CN118324223B - Artificial intelligence-based benzene hydrogenation wastewater desulfurization and deamination treatment method - Google Patents

Artificial intelligence-based benzene hydrogenation wastewater desulfurization and deamination treatment method Download PDF

Info

Publication number
CN118324223B
CN118324223B CN202410732577.5A CN202410732577A CN118324223B CN 118324223 B CN118324223 B CN 118324223B CN 202410732577 A CN202410732577 A CN 202410732577A CN 118324223 B CN118324223 B CN 118324223B
Authority
CN
China
Prior art keywords
tray
monitoring data
reaction environment
environment monitoring
data
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202410732577.5A
Other languages
Chinese (zh)
Other versions
CN118324223A (en
Inventor
王明印
马忠洋
韩宗鑫
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shandong Huineng New Material Technology Co ltd
Original Assignee
Shandong Huineng New Material Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shandong Huineng New Material Technology Co ltd filed Critical Shandong Huineng New Material Technology Co ltd
Priority to CN202410732577.5A priority Critical patent/CN118324223B/en
Publication of CN118324223A publication Critical patent/CN118324223A/en
Application granted granted Critical
Publication of CN118324223B publication Critical patent/CN118324223B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • CCHEMISTRY; METALLURGY
    • C02TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02FTREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02F1/00Treatment of water, waste water, or sewage
    • C02F1/02Treatment of water, waste water, or sewage by heating
    • C02F1/04Treatment of water, waste water, or sewage by heating by distillation or evaporation
    • C02F1/10Treatment of water, waste water, or sewage by heating by distillation or evaporation by direct contact with a particulate solid or with a fluid, as a heat transfer medium
    • CCHEMISTRY; METALLURGY
    • C02TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02FTREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02F1/00Treatment of water, waste water, or sewage
    • C02F1/008Control or steering systems not provided for elsewhere in subclass C02F
    • CCHEMISTRY; METALLURGY
    • C02TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02FTREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02F1/00Treatment of water, waste water, or sewage
    • C02F1/02Treatment of water, waste water, or sewage by heating
    • C02F1/04Treatment of water, waste water, or sewage by heating by distillation or evaporation
    • C02F1/043Details
    • CCHEMISTRY; METALLURGY
    • C02TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02FTREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02F1/00Treatment of water, waste water, or sewage
    • C02F1/20Treatment of water, waste water, or sewage by degassing, i.e. liberation of dissolved gases
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/04Architecture, e.g. interconnection topology
    • G06N3/044Recurrent networks, e.g. Hopfield networks
    • G06N3/0442Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/08Learning methods
    • CCHEMISTRY; METALLURGY
    • C02TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02FTREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02F2101/00Nature of the contaminant
    • C02F2101/10Inorganic compounds
    • C02F2101/101Sulfur compounds
    • CCHEMISTRY; METALLURGY
    • C02TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02FTREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02F2101/00Nature of the contaminant
    • C02F2101/10Inorganic compounds
    • C02F2101/16Nitrogen compounds, e.g. ammonia
    • CCHEMISTRY; METALLURGY
    • C02TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02FTREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
    • C02F2103/00Nature of the water, waste water, sewage or sludge to be treated
    • C02F2103/34Nature of the water, waste water, sewage or sludge to be treated from industrial activities not provided for in groups C02F2103/12 - C02F2103/32
    • C02F2103/36Nature of the water, waste water, sewage or sludge to be treated from industrial activities not provided for in groups C02F2103/12 - C02F2103/32 from the manufacture of organic compounds

Landscapes

  • Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Organic Chemistry (AREA)
  • Chemical & Material Sciences (AREA)
  • Water Supply & Treatment (AREA)
  • Environmental & Geological Engineering (AREA)
  • Hydrology & Water Resources (AREA)
  • Biophysics (AREA)
  • Software Systems (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • General Health & Medical Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Data Mining & Analysis (AREA)
  • Computational Linguistics (AREA)
  • Biomedical Technology (AREA)
  • Artificial Intelligence (AREA)
  • Health & Medical Sciences (AREA)
  • Thermal Sciences (AREA)
  • Physical Water Treatments (AREA)

Abstract

The application relates to the technical field of wastewater treatment, in particular to a benzene hydrogenation wastewater desulfurization and deamination treatment method based on artificial intelligence, which comprises the following steps: the method comprises the steps of collecting reaction environment monitoring data and flow data of a feed inlet of a gas stripping deamination tower, a liquid phase reflux inlet of a separator at each collecting moment, reaction environment monitoring data of each tray at each collecting moment and the horizontal height of each tray, obtaining the steady-state maintenance value of the trays and a strong feed reflux interference coefficient, calculating the steady-state evaluation weight of the trays to obtain steady-state evaluation degree of the same type monitoring data, obtaining the predicted flow of the liquid phase reflux inlet of the separator at the next moment, and adjusting the liquid phase reflux amount of the liquid phase reflux inlet of the separator. The application aims to solve the problem that the control of liquid phase reflux quantity is not accurate enough due to the large fluctuation of reaction environment in the stripping deamination tower.

Description

Artificial intelligence-based benzene hydrogenation wastewater desulfurization and deamination treatment method
Technical Field
The application relates to the technical field of wastewater treatment, in particular to a benzene hydrogenation wastewater desulfurization and deamination treatment method based on artificial intelligence.
Background
The wastewater of the crude benzene hydrogenation process has the characteristics of high amide and high sulfide, and can be discharged only after desulfurization and deamination treatment reaches the discharge standard of a sewage treatment plant. In the treatment process of desulfurizing and deaminizing the wastewater by adopting a stripping method, in order to improve the purity of ammonia-rich gas flowing out of the top end of the stripping deaminizing tower and improve the product quality, a part of ammonia-rich gas is cooled into liquid phase reflux by adopting a separator at an ammonia gas outlet at the top end of the stripping deaminizing tower, so that the ammonia concentration at the top end of the stripping deaminizing tower is stably kept at a higher level. When ammonia water is refluxed through the separator at the top end of the gas stripping deamination tower, the liquid phase reflux quantity of the separator needs to be adjusted in real time according to the inlet wastewater quantity of the gas stripping deamination tower and the gas-liquid phase state in the gas stripping deamination tower. When the liquid phase reflux quantity is too small, the purity of the product ammonia-rich gas can be reduced; when the liquid phase reflux amount is excessive, the working efficiency of the stripping deamination tower is reduced, so that the liquid phase reflux amount of the separator needs to be controlled in real time.
The traditional liquid phase reflux quantity control method controls the liquid phase reflux quantity according to basic sensor parameters such as ammonia nitrogen concentration, PH value and the like in the stripping deamination tower, so that the environment in the stripping deamination tower meets the basic parameters of the reaction, but the control on the liquid phase reflux quantity is not accurate enough due to the large fluctuation of the reaction environment in the stripping deamination tower.
Disclosure of Invention
In view of the above, it is necessary to provide an artificial intelligence-based benzene hydrogenation wastewater desulfurization and deamination treatment method, which improves accuracy of liquid phase reflux amount control compared with a conventional liquid phase reflux amount control method.
The artificial intelligence-based benzene hydrogenation wastewater desulfurization and deamination treatment method adopts the following technical scheme:
One embodiment of the application provides an artificial intelligence-based benzene hydrogenation wastewater desulfurization and deamination treatment method, which comprises the following steps:
Collecting reaction environment monitoring data and flow data of a gas stripping deamination tower feed inlet and a liquid phase reflux port of a separator at each collecting moment, and the reaction environment monitoring data of each tray at each collecting moment, and the horizontal height of each tray;
Acquiring the steady-state maintenance value of each tray at each acquisition moment based on the height difference of adjacent trays and the reaction environment monitoring data;
Acquiring a strong interference coefficient of feed reflux of each reaction environment monitoring data of each tray based on the fluctuation characteristic difference of the same type of reaction environment monitoring data of the feed inlet of the gas stripping deamination tower and the liquid phase reflux of the separator;
Obtaining a tray steady state evaluation weight of any one of the reaction environment monitoring data of any one of the trays according to a feed reflux strong interference coefficient of any one of the reaction environment monitoring data of any one of the trays and a tray steady state maintenance value of any one of the trays at each acquisition time;
based on the tray steady state evaluation weight of each reaction environment monitoring data of each tray and the variation difference of the same type of reaction environment monitoring data of all trays in space at the same acquisition time, acquiring the steady state evaluation degree of the homotype monitoring data of each reaction environment monitoring data at each acquisition time;
And obtaining predicted flow of the liquid phase reflux port of the separator at the next moment according to the steady-state evaluation degree of the homotypic monitoring data of each reaction environment monitoring data at each acquisition moment, the reaction environment monitoring data of the feed inlet of the stripping deamination tower and the liquid phase reflux port of the separator at each acquisition moment and the flow data, and adjusting the liquid phase reflux amount of the liquid phase reflux port of the separator.
In one embodiment, the reaction environment monitoring data includes three types of PH, pressure, and temperature.
In one embodiment, the method for obtaining the steady-state maintenance value of each tray at each collection time comprises the following specific steps:
Recording the absolute value of the difference value of the PH value of any tray and the adjacent next tray at any collecting moment as the PH value attenuation index of any tray at any collecting moment;
Dividing the PH value attenuation index by the height difference between any tray and the next adjacent tray to be used as the deamination effect estimated value of any tray at any collecting time;
The steady-state maintenance value of any tray at any collecting moment respectively forms a negative correlation with the pressure and the temperature of any tray at any collecting moment, and forms a positive correlation with the deamination effect estimated value of any tray at any collecting moment.
In one embodiment, the obtaining the feed reflux strong interference coefficient of each reaction environment monitoring data of each tray comprises:
Acquiring a reaction monitoring time sequence of the feed inlet of the gas stripping deamination tower, the liquid phase reflux inlet of the separator and each tray according to the feed inlet of the gas stripping deamination tower, the liquid phase reflux inlet of the separator and the reaction environment monitoring data of each tray at all acquisition moments;
Obtaining a local fluctuation variation vector of each reaction monitoring time sequence based on the fluctuation characteristics of each reaction monitoring time sequence;
Recording the similarity degree of the local fluctuation variation vectors of the reaction monitoring time sequences corresponding to the same kind of reaction environment monitoring data of the feed inlet of the gas stripping deamination tower as the feed anti-interference coefficient of the corresponding reaction environment monitoring data of each tray, and recording the similarity degree of the local fluctuation variation vectors of the reaction monitoring time sequences corresponding to the same kind of reaction environment monitoring data of the liquid phase reflux inlet of the separator as the reflux anti-interference coefficient of the corresponding reaction environment monitoring data of each tray;
And recording the difference between the feeding anti-interference coefficient and the reflux anti-interference coefficient of any one of the reaction environment monitoring data of any one of the trays as the feeding reflux strong interference coefficient of any one of the reaction environment monitoring data of any one of the trays.
In one embodiment, the method for obtaining each reaction monitoring time sequence of the feed inlet of the stripping deamination tower, the liquid phase reflux mouth of the separator and each tray comprises the following specific steps:
Arranging each reaction environment monitoring data of each tray at all acquisition moments in ascending order according to the acquisition time sequence to be used as each reaction monitoring time sequence of each tray;
and acquiring each reaction monitoring time sequence of the feed inlet of the stripping deamination tower and the liquid phase reflux port of the separator by adopting the same acquisition method as that of each reaction monitoring time sequence of each tray for each reaction environment monitoring data of all acquisition moments of the feed inlet of the stripping deamination tower and the liquid phase reflux port of the separator.
In one embodiment, the method for obtaining the local fluctuation variance vector of each reaction monitoring time sequence includes the following specific steps:
And for each data point in each reaction monitoring time sequence, constructing a sliding window with a preset length by taking any data point as a center, taking the variation coefficient of all the data points in the sliding window as the neighborhood fluctuation variation index of any data point, and arranging the neighborhood fluctuation variation indexes of all the data points in any reaction monitoring time sequence according to the ascending order of time sequence to be taken as the local fluctuation variation vector of any reaction monitoring time sequence.
In one embodiment, the tray steady state evaluation weight of any one of the reaction environment monitoring data of any one of the trays is in a negative correlation with the feed reflux strong interference coefficient of any one of the reaction environment monitoring data of any one of the trays, and in a positive correlation with the tray steady state maintenance value of any one of the trays at each acquisition time.
In one embodiment, the obtaining the steady-state evaluation degree of homotypic monitoring data of each reaction environment monitoring data at each collection time includes:
Acquiring homotypic data space gradient unbalance indexes of each reaction environment monitoring data at each acquisition time based on the space variation difference of the same type of reaction environment monitoring data of all trays at the same acquisition time;
Taking the product of the homotypic data space gradient unbalance index of any one of the reaction environment monitoring data of each tray at each acquisition time and the tray steady state evaluation weight of any one of the reaction environment monitoring data of each tray as the homotypic data space unbalance weighting index of any one of the reaction environment monitoring data of each tray at each acquisition time, and taking the sum of the homotypic data space unbalance weighting indexes of any one of the reaction environment monitoring data of all trays at any one of the acquisition time as the homotypic monitoring data steady state evaluation degree of any one of the reaction environment monitoring data of any one of the acquisition time.
In one embodiment, the acquiring the homotypic data space gradient imbalance index of each reaction environment monitoring data at each acquisition time comprises:
Arranging any one kind of reaction environment monitoring data of all trays at any one collection time according to the ascending sequence of the numbers of the trays, taking the reaction environment monitoring data as a reaction monitoring space sequence of any one kind of reaction environment monitoring data at any one collection time, taking a first order derivative function of the reaction monitoring space sequence as a space gradient sequence of homotype data in a tower, and recording the average value of all data values in the space gradient sequence of homotype data in the tower as a space average gradient index of homotype data in the tower of any one kind of reaction environment monitoring data at any one collection time;
And marking the difference between each data value of the in-tower homotype data space gradient sequence and the average homotype data space gradient index in the tower as the homotype data space gradient unbalance index of any one reaction environment monitoring data of each tower tray at any acquisition time.
In one embodiment, the method for obtaining the predicted flow of the liquid phase reflux port of the separator at the next moment and adjusting the liquid phase reflux amount of the liquid phase reflux port of the separator includes the following specific steps:
And taking the homotypic monitoring data steady-state evaluation degree of each type of reaction environment monitoring data acquired in real time, the reaction environment monitoring data and the flow data of the feeding port of the stripping deamination tower and the reaction environment monitoring data of the liquid phase reflux port of the separator as inputs of a long-short-term memory neural network model, outputting the predicted flow of the liquid phase reflux port of the separator at the next moment, and adjusting the liquid phase reflux quantity of the liquid phase reflux port of the separator.
The application has the following beneficial effects:
The embodiment of the application provides a benzene hydrogenation wastewater desulfurization and deamination treatment method based on artificial intelligence, which comprises the following steps: measuring deamination efficiency of each tray by the change rate of PH value between adjacent trays in the stripping deamination tower, measuring energy consumption of the trays by temperature and pressure, analyzing the deamination efficiency and the energy consumption of each tray, and acquiring the tray steady-state maintenance value of each tray at each acquisition time based on the height difference of the adjacent trays and the reaction environment monitoring data to measure the necessity of maintaining the vapor-liquid phase reaction environment steady state of each tray at each acquisition time; the method comprises the steps of obtaining a strong feed reflux interference coefficient of each reaction environment monitoring data of each tray based on the fluctuation characteristic difference of the same type of reaction environment monitoring data of each tray and a feed inlet and a liquid phase reflux of a separator of the gas stripping deamination tower, and measuring the influence degree of the reaction environment monitoring data of each tray on the feed inlet and the liquid phase reflux of the separator of the gas stripping deamination tower, so that the steady state evaluation weight of each reaction environment monitoring data of each tray is obtained according to the strong feed reflux interference coefficient of each reaction environment monitoring data of each tray and the steady state maintenance value of each tray at each acquisition time, and the obtained benefits of maintaining the reaction environment of each tray are distinguished, so that the steady state of the reaction environment inside the gas stripping deamination tower can be ensured by smaller reflux liquid phase flow adjustment when the liquid phase reflux of the gas stripping deamination tower is controlled, and the deamination efficiency of the gas stripping deamination tower is improved; considering that the internal reaction environment system of the stripping deamination tower is distributed in a gradient manner from top to bottom, based on the tray steady state evaluation weight of each reaction environment monitoring data of each tray and the variation difference of the same type of reaction environment monitoring data of all trays at the same collection time in space, obtaining the steady state evaluation degree of each reaction environment monitoring data at each collection time, and evaluating the stability of each reaction environment monitoring data of the whole stripping deamination tower at each collection time, wherein different weights are set for each reaction environment monitoring data of each tray according to the difference of the influence degree of a feed inlet or a liquid phase reflux port of the stripping deamination tower and the difference of treatment wastewater energy consumption, thereby improving the reliability of the stability degree evaluation of each reaction environment monitoring data of the stripping deamination tower at different collection times; according to the steady-state evaluation degree of the homotypic monitoring data of each reaction environment monitoring data at each acquisition time, the reaction environment monitoring data of the feed inlet of the stripping deamination tower and the liquid phase reflux inlet of the separator at each acquisition time and the predicted flow of the liquid phase reflux inlet of the separator at the next time, the liquid phase reflux amount of the liquid phase reflux inlet of the separator is adjusted, the fluctuation of the reaction environment in the stripping deamination tower is fully considered, and the accuracy of controlling the liquid phase reflux amount of the stripping deamination tower is improved.
Drawings
In order to more clearly illustrate the embodiments of the application or the technical solutions of the prior art, the drawings which are used in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only some embodiments of the application, and that other drawings can be obtained according to these drawings without inventive faculty for a person skilled in the art.
FIG. 1 is a schematic flow chart of a benzene hydrogenation wastewater desulfurization and deamination treatment method based on artificial intelligence according to an embodiment of the application;
FIG. 2 is a flow chart of the desulfurization and deamination process of benzene hydrogenation wastewater;
Fig. 3 to 11 are schematic diagrams of reaction monitoring time sequences corresponding to temperature data;
Fig. 12-20 are schematic diagrams of homotypic data space gradient imbalance indexes of temperature data.
Detailed Description
In describing embodiments of the present application, words such as "exemplary," "or," "such as," and the like are used to mean serving as an example, instance, or illustration. Any embodiment or design described herein as "exemplary" or "for example" should not be construed as preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary," "or," "such as," and the like are intended to present related concepts in a concrete fashion.
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 application belongs. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. It is to be understood that, unless otherwise indicated, a "/" means or. For example, A/B may represent A or B. The "and/or" in the present application is merely one association relationship describing the association object, indicating that three relationships may exist. For example, a and/or B may represent: a exists alone, A and B exist simultaneously, and B exists alone. "at least one" means one or more. "plurality" means two or more than two. For example, at least one of a, b or c may represent: seven cases of a, b, c, a and b, a and c, b and c, a, b and c.
It should be further noted that the terms "first" and "second" are used herein to distinguish similar objects from each other and are not used to describe a particular order or sequence. The method disclosed in the embodiments of the present application or the method shown in the flowchart, including one or more steps for implementing the method, may be performed in an order that the steps may be interchanged with one another, and some steps may be deleted without departing from the scope of the claims.
Referring to fig. 1, a flow chart of a benzene hydrogenation wastewater desulfurization and deamination treatment method based on artificial intelligence according to an embodiment of the application is shown, and the method comprises the following steps:
And S001, collecting reaction environment monitoring data and flow data of a feed inlet of the stripping deamination tower, a liquid phase reflux inlet of the separator at each collecting moment, reaction environment monitoring data of each tray at each collecting moment and the horizontal height of each tray.
The treatment process of benzene hydrogenation wastewater desulfurization and deamination sequentially comprises the steps of raw material preheating, deacidification of a deacidification tower, adjustment of the PH value of deacidification kettle liquid by an alkali liquor tank, deamination of the deamination tower, condensation of ammonia-rich steam of the deamination tower by a condenser, collection of ammonia water by an ammonia water buffer tank and an ammonia water storage tank, and the like. In one embodiment of the application, a flow chart of the desulfurization and deamination process of benzene hydrogenation wastewater is shown in fig. 2.
The method comprises the steps of numbering all trays according to the sequence from top to bottom, respectively installing a group of reaction environment monitoring sensors at a feed inlet of the gas stripping deamination tower, a liquid phase reflux port of a separator and each tray, additionally installing a flow sensor at the feed inlet of the gas stripping deamination tower and the liquid phase reflux port of the separator, acquiring reaction environment monitoring data and flow data once every T seconds, recording the level of each tray, and acquiring T times.
It should be noted that, the collection interval T and the collection times T are all preset values, and each set of reaction environment monitoring sensors includes a PH value sensor, a temperature sensor, and a pressure sensor, and the reaction environment monitoring data includes PH value, temperature, and pressure. In this embodiment, the collection interval T takes 1 second, the collection times T takes 10000, the pH value sensor adopts a pH sensor InPro3250i/SG/120 liquid pH sensor, the temperature sensor adopts a WRP-130PG high temperature sensor, the pressure sensor adopts a KZY-KG high temperature pressure sensor, the flow sensor adopts a KZV vortex street flow sensor, and for the collection interval and the selection of the sensors, as other embodiments, the practitioner can select the flow sensor by himself, and the application is not limited in particular.
And step S002, obtaining the steady-state maintenance value of each tray at each acquisition time based on the height difference of the adjacent trays and the reaction environment monitoring data.
In order to control the flow rate of the reflux liquid phase to ensure the stability of the reaction system in the stripping deamination tower, the stability degree of the reaction system in the stripping deamination tower needs to be evaluated. The traditional liquid phase reflux quantity control method controls the liquid phase reflux quantity according to basic sensor parameters such as ammonia nitrogen concentration, PH value and the like in the stripping deamination tower, only the integral reaction condition of the stripping deamination tower is considered, the internal reaction environment system of the stripping deamination tower is distributed in a gradient mode from top to bottom, when the gradient distribution is disturbed, the traditional liquid phase reflux quantity control method cannot accurately regulate the liquid phase reflux quantity, so that deamination efficiency is low, and therefore structural distribution characteristics of the internal reaction system of the stripping deamination tower need to be analyzed.
It should be noted that, the PH value, pressure and temperature in different trays of the stripping deamination tower are different, the efficiency of evaporating ammonia from the waste liquid in different trays is also different, and when keeping the steady state of the reaction environment in the stripping deamination tower, the tray with higher efficiency of evaporating ammonia should be maintained with emphasis, so as to improve the deamination efficiency of the stripping deamination tower to the greatest extent.
Specifically, the absolute value of the difference value between the PH value of any tray and the PH value of the next adjacent tray at any collecting time is recorded as the PH value attenuation index of any tray at any collecting time, and the PH value attenuation index is divided by the height difference between any tray and the next adjacent tray to be used as the deamination effect estimated value of any tray at any collecting time. The steady-state maintenance value of any tray at any collecting moment respectively forms a negative correlation with the pressure and the temperature of any tray at any collecting moment and forms a positive correlation with the deamination effect estimated value of any tray at any collecting moment.
It should be understood that the positive correlation refers to the relationship between the independent variable and the dependent variable, and when the independent variable increases or decreases, the dependent variable also increases or decreases, that is, the changing directions of the two variables are the same, and the positive correlation may be a multiplication relationship, an addition relationship, a proportional relationship, or the like, which is not particularly limited in the present application. The negative correlation indicates that the dependent variable decreases with increasing independent variable, and the dependent variable increases with decreasing independent variable, which may be a subtraction relationship, a division relationship, or the like, and is determined by the actual application.
As one embodiment of the application, the absolute value of the difference value of the PH value of any tray and the adjacent next tray at any collecting moment is recorded as the PH value attenuation index of any tray at any collecting moment; as another embodiment of the application, the PH value ratio of any tray to the next adjacent tray at any collecting time is recorded as PH value relative index, and the absolute value of the difference value between the PH value relative index and the number 1 is recorded as PH value attenuation index of any tray at any collecting time. And adding a parameter adjusting factor to the product of the temperature and the pressure of any tray at any collecting moment to be used as an ammonia evaporation energy consumption index of the any tray at any collecting moment, and dividing the PH value attenuation index of any tray at any collecting moment by the ammonia evaporation energy consumption index to be used as the steady-state maintenance value of the tray at any collecting moment.
The ammonia gas flows upwards through evaporation, and when the height difference between the tray and the next adjacent tray is smaller and the PH value difference is larger, the ammonia removal effect of the tray is better, the ammonia removal effect estimated value is larger, and the steady-state maintenance value of the tray is larger; when the temperature and the pressure of the tower tray are higher, the efficiency of evaporating ammonia gas is lower, the energy consumption for maintaining the steady state of the vapor-liquid phase reaction environment is higher, the steady state of the reaction environment of other tower trays is maintained to perform wastewater deamination, so that the purposes of reducing the energy consumption of the stripping deamination tower and improving the deamination efficiency are achieved, and the steady state maintenance value of the tower tray is lower.
It should be further noted that, the greater the steady-state maintenance value of the tray at a certain collection time, the more energy-saving the tray can complete the deamination treatment of the wastewater at the collection time, and the more attention should be paid to maintaining the reaction environment at the tray when the steady-state reaction environment inside the stripping deamination tower is regulated.
And S003, obtaining a strong interference coefficient of feed reflux of each reaction environment monitoring data of each tray based on the fluctuation characteristic difference of the reaction environment monitoring data of the same type of each tray, the feed inlet of the stripping deamination tower and the liquid phase reflux of the separator.
Because the distances between different trays and the reflux port and between different trays and the feed inlet are different, when the distance between the trays and the reflux port is farther and the distance between the trays and the reflux port is closer, the reaction environment of the trays is more easily influenced by the change of the wastewater flow rate or the chemical property change of the feed inlet, the stability of the reaction environment of the trays is more difficult to maintain through liquid phase reflux, and the cost is higher when the reaction environment of the trays is maintained, so that the weight of the trays is smaller when the stability of the whole environment of the stripping tower is evaluated.
Specifically, each reaction environment monitoring data of each tray at all the acquisition time is arranged in ascending order according to the acquisition time sequence, and is used as each reaction monitoring time sequence of each tray. The method for acquiring each reaction monitoring time sequence of the feed inlet of the stripping deamination tower, the liquid phase reflux inlet of the separator and each tray is the same. In an embodiment of the application, schematic diagrams of the reaction monitoring time sequence corresponding to the temperature data are shown in fig. 3 to 11. And T1-T9 sequentially correspond to reaction monitoring time sequences corresponding to temperature data of the 1-9 th trays, wherein the transverse axis of each reaction monitoring time sequence is the acquisition time, and the longitudinal axis is the temperature.
Further, for each data point in each reaction monitoring time sequence, a sliding window with the length of w is built by taking any data point as a center, the variation coefficient of all the data points in the sliding window is used as the neighborhood fluctuation variation index of any data point, and the neighborhood fluctuation variation indexes of all the data points in any reaction monitoring time sequence are arranged in ascending order according to the time sequence to be used as the local fluctuation variation vector of any reaction monitoring time sequence.
The method comprises the steps of recording the similarity degree of local fluctuation variation vectors of reaction monitoring time sequences corresponding to the same-kind reaction environment monitoring data of feed inlets of a gas stripping deamination tower as feed anti-interference coefficients of the corresponding reaction environment monitoring data of each tray, recording the similarity degree of the local fluctuation variation vectors of the reaction monitoring time sequences corresponding to the same-kind reaction environment monitoring data of liquid phase reflux ports of a separator as reflux anti-interference coefficients of the corresponding reaction environment monitoring data of each tray, and recording the absolute value of the difference value of the feed anti-interference coefficients and the reflux anti-interference coefficients of any one kind of reaction environment monitoring data of any tray as feed reflux strong interference coefficients of any kind of reaction environment monitoring data of any tray.
It should be noted that, the calculation of the similarity between the vectors is known, the length w of the sliding window is an artificially preset odd number, the cosine similarity is selected for the calculation of the similarity between the vectors in this embodiment, the value of the length of the sliding window is 11, and the calculation of the similarity between the vectors and the value of the length of the sliding window can be selected by the practitioner as other embodiments, which are not particularly limited in this application.
It should be further noted that, the local fluctuation variation vector of each reaction environment monitoring data of each tray represents the fluctuation characteristic of the reaction environment monitoring data of the type of the tray, and when the degree of similarity between the tray and the fluctuation characteristic of certain reaction environment monitoring data of the feed inlet of the stripping deamination tower is larger and the degree of similarity between the tray and the fluctuation characteristic of the same kind of reaction environment monitoring data of the liquid phase reflux mouth of the separator is smaller, the more likely that the reaction environment monitoring data of the type of the tray is extremely influenced by the feed inlet of the stripping deamination tower is illustrated, and the feed reflux strong interference coefficient value is larger; when the smaller the similarity of the fluctuation characteristics of certain reaction environment monitoring data of the tray and the feed inlet of the stripping deamination tower is, the larger the similarity of the fluctuation characteristics of the same reaction environment monitoring data of the liquid phase reflux mouth of the separator is, the more likely the reaction environment monitoring data of the type of the tray is influenced by the extreme influence of the liquid phase reflux mouth of the separator is, and the larger the feed reflux strong interference coefficient value is.
And S004, acquiring tray steady state evaluation weight of any one of the reaction environment monitoring data of any one of the trays according to the feed reflux strong interference coefficient of any one of the reaction environment monitoring data of any one of the trays at each acquisition moment of tray steady state maintenance value of any one of the trays.
Further, the tray steady state evaluation weight of any one of the reaction environment monitoring data of any one of the trays is in a negative correlation with the feed reflux strong interference coefficient of any one of the reaction environment monitoring data of any one of the trays, and is in a positive correlation with the tray steady state maintenance value of any one of the trays at each acquisition time.
As one embodiment of the application, the average value of the steady-state maintenance values of any tray at all acquisition moments is recorded as the average index of the steady-state maintenance values of any tray, and the ratio of the average index of the steady-state maintenance values of any tray to the feed reflux strong interference coefficient of any one of the reaction environment monitoring data of any tray is recorded as the tray steady-state evaluation weight of any one of the reaction environment monitoring data of any tray.
It should be noted that, when the feed reflux strong interference coefficient of certain reaction environment monitoring data of the tray is larger, the more likely that the type of reaction environment monitoring data of the tray is affected by the liquid phase reflux port of the separator, the more likely that the type of reaction environment monitoring data of the tray is affected by the feed port of the stripping deamination tower or the liquid phase reflux port of the separator, the smaller weight should be set when the stability of the overall environment of the stripping deamination tower is evaluated, and the smaller the steady state evaluation weight value of the tray is; when the tray steady-state maintenance value of the tray at each collection time is larger, the tray can finish deamination treatment of wastewater with lower energy consumption, and when the stability of the overall environment of the stripping deamination tower is evaluated, the tray should be provided with larger weight.
Step S005, based on the tray steady state evaluation weight of each reaction environment monitoring data of each tray and the variation difference of the same type of reaction environment monitoring data of all trays in space at the same acquisition time, acquiring the steady state evaluation degree of the homotype monitoring data of each reaction environment monitoring data at each acquisition time.
Specifically, any one of the reaction environment monitoring data of all trays at any one of the collection moments is arranged according to the ascending order of the numbers of the trays, the first order derivative function of the reaction monitoring space sequence is used as a space gradient sequence of the same type data in the tower, the average value of all the data values in the space gradient sequence of the same type data in the tower is recorded as the space average gradient index of the same type data in the tower of any one of the reaction environment monitoring data at any one of the collection moments, and the absolute value of the difference value between each data value of the space gradient sequence of the same type data in the tower and the space average gradient index of the same type data in the tower is recorded as the space gradient unbalance index of the same type data of any one of the reaction environment monitoring data of each tray at any one of the collection moments. In one embodiment of the present application, a schematic diagram of the homotype data space gradient imbalance index of the temperature data is shown in fig. 12 to 20. The time series formed by the homotype data space gradient unbalance indexes of the temperature data of the 1 st tray to the 9 th tray at all acquisition moments are sequentially corresponding to P1 to P9, the horizontal axis of each time series is the acquisition moment, and the vertical axis is the homotype data space gradient unbalance index.
It should be noted that, the length of each reaction monitoring space sequence is equal to the number of trays, the first order derivative function represents the speed of sequence change, and when the change speed of the same reaction environment monitoring data of each tray at the same collection time in space deviates from the average change speed, the more unstable the type of reaction environment monitoring data of the tray at the collection time is, the larger the homotype data space gradient unbalance index value is.
Further, taking the product of the homotypic data space gradient unbalance index of any one of the reaction environment monitoring data of each tray at each acquisition time and the tray steady state evaluation weight of any one of the reaction environment monitoring data of each tray as the homotypic data space unbalance weighting index of any one of the reaction environment monitoring data of each tray at each acquisition time, and taking the sum of the homotypic data space unbalance weighting indexes of any one of the reaction environment monitoring data of all trays at any one of the acquisition time as the homotypic monitoring data steady state evaluation degree of any one of the reaction environment monitoring data of any one of the acquisition time.
It should be noted that, taking the tray steady state evaluation weight of each reaction environment monitoring data of each tray as the weight, carrying out weighted summation on the homotypic data space gradient unbalance indexes of the same type of reaction environment monitoring data of all trays at the same collection time to obtain the homotypic monitoring data steady state evaluation degree of each reaction environment monitoring data of each collection time, so as to measure the stability degree of each reaction environment monitoring data of the stripping deamination tower at different collection times, and setting different weights for each reaction environment monitoring data of each tray according to the different influence degrees of the feed inlet or the liquid phase reflux inlet of the separator and the different treatment waste water energy consumption of the stripping deamination tower, thereby improving the reliability of the stability degree evaluation of each reaction environment monitoring data of the stripping deamination tower at different collection times.
Step S006, according to the steady-state evaluation degree of the homotypic monitoring data of each reaction environment monitoring data at each acquisition time, and the reaction environment monitoring data and the flow data of the feed inlet of the stripping deamination tower and the liquid phase reflux inlet of the separator at each acquisition time, obtaining the predicted flow of the liquid phase reflux inlet of the separator at the next time, and adjusting the liquid phase reflux amount of the liquid phase reflux inlet of the separator.
Taking the steady-state evaluation degree of the homotypic monitoring data of each reaction environment monitoring data at each acquisition time, the reaction environment monitoring data and the flow data of the feeding port of the stripping deamination tower at each acquisition time and the reaction environment monitoring data of the liquid-phase return port of the separator at each acquisition time as inputs of a long-short-time memory neural network model, outputting the predicted flow of the liquid-phase return port of the separator at the next acquisition time at each acquisition time, taking the mean square error of the flow data and the predicted flow of the liquid-phase return port of the separator at the next acquisition time at each acquisition time as a loss function of the long-short-time memory neural network model, and training the long-short-time memory neural network model.
It should be noted that, training of the long-short-term memory neural network model is a well-known technique, in this embodiment, a ReLU function is used for the activation function of the long-short-term memory neural network model, and a Adma optimizer is used as an optimizer, so that an implementer can select the long-short-term memory neural network model by himself, and the present application is not limited in this respect.
Further, the steady-state evaluation degree of the homotypic monitoring data of each reaction environment monitoring data acquired in real time, the reaction environment monitoring data and the flow data of the feed inlet of the stripping deamination tower and the reaction environment monitoring data of the liquid phase reflux inlet of the separator are used as inputs of a long-short-term memory neural network model after training is completed, the predicted flow of the liquid phase reflux inlet of the separator at the next moment is output, and the liquid phase reflux amount of the liquid phase reflux inlet of the separator is adjusted.
The embodiment of the application provides a benzene hydrogenation wastewater desulfurization and deamination treatment method based on artificial intelligence, which comprises the following steps: measuring deamination efficiency of each tray by the change rate of PH value between adjacent trays in the stripping deamination tower, measuring energy consumption of the trays by temperature and pressure, analyzing the deamination efficiency and the energy consumption of each tray, and acquiring the tray steady-state maintenance value of each tray at each acquisition time based on the height difference of the adjacent trays and the reaction environment monitoring data to measure the necessity of maintaining the vapor-liquid phase reaction environment steady state of each tray at each acquisition time; the method comprises the steps of obtaining a strong feed reflux interference coefficient of each reaction environment monitoring data of each tray based on the fluctuation characteristic difference of the same type of reaction environment monitoring data of each tray and a feed inlet and a liquid phase reflux of a separator of the gas stripping deamination tower, and measuring the influence degree of the reaction environment monitoring data of each tray on the feed inlet and the liquid phase reflux of the separator of the gas stripping deamination tower, so that the steady state evaluation weight of each reaction environment monitoring data of each tray is obtained according to the strong feed reflux interference coefficient of each reaction environment monitoring data of each tray and the steady state maintenance value of each tray at each acquisition time, and the obtained benefits of maintaining the reaction environment of each tray are distinguished, so that the steady state of the reaction environment inside the gas stripping deamination tower can be ensured by smaller reflux liquid phase flow adjustment when the liquid phase reflux of the gas stripping deamination tower is controlled, and the deamination efficiency of the gas stripping deamination tower is improved; considering that the internal reaction environment system of the stripping deamination tower is distributed in a gradient manner from top to bottom, based on the tray steady state evaluation weight of each reaction environment monitoring data of each tray and the variation difference of the same type of reaction environment monitoring data of all trays at the same collection time in space, obtaining the steady state evaluation degree of each reaction environment monitoring data at each collection time, and evaluating the stability of each reaction environment monitoring data of the whole stripping deamination tower at each collection time, wherein different weights are set for each reaction environment monitoring data of each tray according to the difference of the influence degree of a feed inlet or a liquid phase reflux port of the stripping deamination tower and the difference of treatment wastewater energy consumption, thereby improving the reliability of the stability degree evaluation of each reaction environment monitoring data of the stripping deamination tower at different collection times; according to the steady-state evaluation degree of the homotypic monitoring data of each reaction environment monitoring data at each acquisition time, the reaction environment monitoring data of the feed inlet of the stripping deamination tower and the liquid phase reflux inlet of the separator at each acquisition time, and the predicted flow of the liquid phase reflux inlet of the separator at the next time, the liquid phase reflux amount of the liquid phase reflux inlet of the separator is adjusted, the fluctuation of the reaction environment in the stripping deamination tower is fully considered, and the accuracy of controlling the liquid phase reflux amount of the stripping deamination tower is improved.
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. In the description corresponding to the flowcharts and block diagrams in the figures, operations or steps corresponding to different blocks may also occur in different orders than that disclosed in the description, and sometimes no specific order exists between different operations or steps. For example, two consecutive operations or steps may actually be performed substantially in parallel, they may sometimes be performed in reverse order, which may be dependent on the functions involved. Each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
It will be evident to those skilled in the art that the application is not limited to the details of the foregoing illustrative embodiments, and that the present application may be embodied in other specific forms without departing from the essential characteristics thereof. The above-described embodiments of the application should therefore be regarded as illustrative in all respects and not restrictive.

Claims (2)

1. The artificial intelligence-based benzene hydrogenation wastewater desulfurization and deamination treatment method is characterized by comprising the following steps of:
Collecting reaction environment monitoring data and flow data of a gas stripping deamination tower feed inlet and a liquid phase reflux port of a separator at each collecting moment, and the reaction environment monitoring data of each tray at each collecting moment, and the horizontal height of each tray;
Acquiring the steady-state maintenance value of each tray at each acquisition moment based on the height difference of adjacent trays and the reaction environment monitoring data;
Acquiring a strong interference coefficient of feed reflux of each reaction environment monitoring data of each tray based on the fluctuation characteristic difference of the same type of reaction environment monitoring data of the feed inlet of the gas stripping deamination tower and the liquid phase reflux of the separator;
Obtaining a tray steady state evaluation weight of any one of the reaction environment monitoring data of any one of the trays according to a feed reflux strong interference coefficient of any one of the reaction environment monitoring data of any one of the trays and a tray steady state maintenance value of any one of the trays at each acquisition time;
based on the tray steady state evaluation weight of each reaction environment monitoring data of each tray and the variation difference of the same type of reaction environment monitoring data of all trays in space at the same acquisition time, acquiring the steady state evaluation degree of the homotype monitoring data of each reaction environment monitoring data at each acquisition time;
According to the steady-state evaluation degree of the homotypic monitoring data of each reaction environment monitoring data at each acquisition time, and the reaction environment monitoring data and the flow data of the feed inlet of the stripping deamination tower and the liquid phase reflux inlet of the separator at each acquisition time, the predicted flow of the liquid phase reflux inlet of the separator at the next time is obtained, and the liquid phase reflux amount of the liquid phase reflux inlet of the separator is adjusted;
The reaction environment monitoring data comprise three types of PH value, pressure and temperature;
the method for acquiring the steady-state maintenance value of the tray at each acquisition time of each tray comprises the following specific steps:
Recording the absolute value of the difference value of the PH value of any tray and the adjacent next tray at any collecting moment as the PH value attenuation index of any tray at any collecting moment;
Dividing the PH value attenuation index by the height difference between any tray and the next adjacent tray to be used as the deamination effect estimated value of any tray at any collecting time;
The steady-state maintenance value of any tray at any collecting moment respectively forms a negative correlation with the pressure and the temperature of any tray at any collecting moment and forms a positive correlation with the deamination effect estimated value of any tray at any collecting moment;
the obtaining the feed reflux strong interference coefficient of each reaction environment monitoring data of each tray comprises the following steps:
Acquiring a reaction monitoring time sequence of the feed inlet of the gas stripping deamination tower, the liquid phase reflux inlet of the separator and each tray according to the feed inlet of the gas stripping deamination tower, the liquid phase reflux inlet of the separator and the reaction environment monitoring data of each tray at all acquisition moments;
Obtaining a local fluctuation variation vector of each reaction monitoring time sequence based on the fluctuation characteristics of each reaction monitoring time sequence;
Recording the similarity degree of the local fluctuation variation vectors of the reaction monitoring time sequences corresponding to the same kind of reaction environment monitoring data of the feed inlet of the gas stripping deamination tower as the feed anti-interference coefficient of the corresponding reaction environment monitoring data of each tray, and recording the similarity degree of the local fluctuation variation vectors of the reaction monitoring time sequences corresponding to the same kind of reaction environment monitoring data of the liquid phase reflux inlet of the separator as the reflux anti-interference coefficient of the corresponding reaction environment monitoring data of each tray;
recording the absolute value of the difference between the feed anti-interference coefficient and the reflux anti-interference coefficient of any one of the reaction environment monitoring data of any one of the trays as the feed reflux strong interference coefficient of any one of the reaction environment monitoring data of any one of the trays;
the tray steady state evaluation weight of any one of the reaction environment monitoring data of any one of the trays and the feed reflux strong interference coefficient of any one of the reaction environment monitoring data of any one of the trays form a negative correlation, and the tray steady state evaluation weight of any one of the trays and the tray steady state maintenance value of any one of the trays at each acquisition time form a positive correlation;
the obtaining the steady-state evaluation degree of the homotypic monitoring data of each reaction environment monitoring data at each acquisition time comprises the following steps:
Acquiring homotypic data space gradient unbalance indexes of each reaction environment monitoring data at each acquisition time based on the space variation difference of the same type of reaction environment monitoring data of all trays at the same acquisition time;
taking the product of the homotypic data space gradient unbalance index of any one of the reaction environment monitoring data of each tray at each acquisition time and the tray steady state evaluation weight of any one of the reaction environment monitoring data of each tray as the homotypic data space unbalance weighting index of any one of the reaction environment monitoring data of each tray at each acquisition time, and taking the sum of the homotypic data space unbalance weighting indexes of any one of the reaction environment monitoring data of all trays at any one of the acquisition time as the homotypic monitoring data steady state evaluation degree of any one of the reaction environment monitoring data of any one of the acquisition time;
the method for obtaining the predicted flow of the liquid phase reflux port of the separator at the next moment and adjusting the liquid phase reflux amount of the liquid phase reflux port of the separator comprises the following specific steps:
Taking the steady-state evaluation degree of the homotypic monitoring data of each reaction environment monitoring data acquired in real time, the reaction environment monitoring data and the flow data of the feed inlet of the stripping deamination tower and the reaction environment monitoring data of the liquid phase reflux inlet of the separator as inputs of a long-short-term memory neural network model, outputting the predicted flow of the liquid phase reflux inlet of the separator at the next moment, and adjusting the liquid phase reflux amount of the liquid phase reflux inlet of the separator;
The method for obtaining the local fluctuation variation vector of each reaction monitoring time sequence comprises the following specific steps:
For each data point in each reaction monitoring time sequence, constructing a sliding window with a preset length by taking any data point as a center, taking the variation coefficient of all the data points in the sliding window as the neighborhood fluctuation variation index of any data point, and arranging the neighborhood fluctuation variation indexes of all the data points in any reaction monitoring time sequence according to the ascending order of time sequence to be taken as the local fluctuation variation vector of any reaction monitoring time sequence;
the step of obtaining the homotypic data space gradient unbalance index of each reaction environment monitoring data at each acquisition time comprises the following steps:
Arranging any one kind of reaction environment monitoring data of all trays at any one collection time according to the ascending sequence of the numbers of the trays, taking the reaction environment monitoring data as a reaction monitoring space sequence of any one kind of reaction environment monitoring data at any one collection time, taking a first order derivative function of the reaction monitoring space sequence as a space gradient sequence of homotype data in a tower, and recording the average value of all data values in the space gradient sequence of homotype data in the tower as a space average gradient index of homotype data in the tower of any one kind of reaction environment monitoring data at any one collection time;
And recording the absolute value of the difference between each data value of the in-tower homotype data space gradient sequence and the average homotype data space gradient index in the tower as the homotype data space gradient unbalance index of any one reaction environment monitoring data of each tower tray at any acquisition moment.
2. The artificial intelligence based benzene hydrogenation wastewater desulfurization and deamination treatment method of claim 1, wherein the method for obtaining each reaction monitoring time sequence of a feed inlet of a stripping deamination tower, a liquid phase reflux port of a separator and each tray comprises the following specific steps:
Arranging each reaction environment monitoring data of each tray at all acquisition moments in ascending order according to the acquisition time sequence to be used as each reaction monitoring time sequence of each tray;
and acquiring each reaction monitoring time sequence of the feed inlet of the stripping deamination tower and the liquid phase reflux port of the separator by adopting the same acquisition method as that of each reaction monitoring time sequence of each tray for each reaction environment monitoring data of all acquisition moments of the feed inlet of the stripping deamination tower and the liquid phase reflux port of the separator.
CN202410732577.5A 2024-06-07 2024-06-07 Artificial intelligence-based benzene hydrogenation wastewater desulfurization and deamination treatment method Active CN118324223B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202410732577.5A CN118324223B (en) 2024-06-07 2024-06-07 Artificial intelligence-based benzene hydrogenation wastewater desulfurization and deamination treatment method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202410732577.5A CN118324223B (en) 2024-06-07 2024-06-07 Artificial intelligence-based benzene hydrogenation wastewater desulfurization and deamination treatment method

Publications (2)

Publication Number Publication Date
CN118324223A CN118324223A (en) 2024-07-12
CN118324223B true CN118324223B (en) 2024-09-06

Family

ID=91769566

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202410732577.5A Active CN118324223B (en) 2024-06-07 2024-06-07 Artificial intelligence-based benzene hydrogenation wastewater desulfurization and deamination treatment method

Country Status (1)

Country Link
CN (1) CN118324223B (en)

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104355321A (en) * 2014-10-23 2015-02-18 中冶焦耐工程技术有限公司 Technology and device for producing stronger ammonia water with controllable concentration by scrubbing ammonia through ammonium phosphate
CN109508811A (en) * 2018-09-30 2019-03-22 中冶华天工程技术有限公司 Parameter prediction method is discharged based on principal component analysis and the sewage treatment of shot and long term memory network

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2015052279A1 (en) * 2013-10-10 2015-04-16 Universitat Autonoma De Barcelona A method and a system for wastewater nitrogen removal
CN205145959U (en) * 2015-10-21 2016-04-13 济南冶金化工设备有限公司 Coking flue gas and processing economic benefits and social benefits clean system that unifies including ammonia wastewater
CN212050954U (en) * 2020-04-13 2020-12-01 湖北泰盛化工有限公司 Ammonia water resource utilization device
CN112354332B (en) * 2020-11-03 2023-04-18 江南环保集团股份有限公司 Method for applying membrane separation device to ammonia desulphurization
CN117003324A (en) * 2023-10-07 2023-11-07 北京赛科康仑环保科技有限公司 Artificial intelligent control method and system for ammonia nitrogen wastewater treatment
CN117193443B (en) * 2023-11-06 2024-01-26 山东汇能新材料科技股份有限公司 Pure benzene storage environment control system based on artificial intelligence

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104355321A (en) * 2014-10-23 2015-02-18 中冶焦耐工程技术有限公司 Technology and device for producing stronger ammonia water with controllable concentration by scrubbing ammonia through ammonium phosphate
CN109508811A (en) * 2018-09-30 2019-03-22 中冶华天工程技术有限公司 Parameter prediction method is discharged based on principal component analysis and the sewage treatment of shot and long term memory network

Also Published As

Publication number Publication date
CN118324223A (en) 2024-07-12

Similar Documents

Publication Publication Date Title
CN100458603C (en) Corn drying prediction control system and method based on fuzzy-neural network
CN109740661B (en) Oil well moving liquid level self-adaptive prediction method based on fuzzy evaluation
CN107358021B (en) DO prediction model establishment method based on BP neural network optimization
CN114275912B (en) Aeration system dissolved oxygen control method based on adaptive neural network model
Alatiqi et al. Process control in water desalination industry: an overview
CN109492265B (en) Wastewater effluent index prediction method based on dynamic nonlinear PLS soft measurement method
CN110889085A (en) Intelligent wastewater monitoring method and system based on complex network multiple online regression
CN107451682B (en) Urban tidal river reach ecological water demand prediction method based on neural network
CN103808380B (en) A kind of flow fast tracking method for ultrasonic flow rate measuring instrument
CN102313796A (en) Soft measuring method of biochemical oxygen demand in sewage treatment
CN110981021B (en) Intelligent dosing system and method for advanced wastewater oxidation treatment based on fuzzy BP neural network
CN113807545A (en) River and lake ecological flow forecasting and early warning method based on deep learning and physical model
CN112782975A (en) Sewage treatment aeration intelligent control method and system based on deep learning
CN106096730A (en) A kind of intelligent detecting method of MBR film permeability rate based on Recurrent RBF Neural Networks
CN118324223B (en) Artificial intelligence-based benzene hydrogenation wastewater desulfurization and deamination treatment method
CN101929993A (en) Dynamic fuzzy neural network based penicillin fermentation process soft measuring modeling method
CN109917656B (en) Circulating cooling water minimum pressure difference energy-saving control system and method based on process medium multi-temperature target
CN111125907A (en) Sewage treatment ammonia nitrogen soft measurement method based on hybrid intelligent model
CN115206444A (en) Optimal drug dosage prediction method based on FCM-ANFIS model
CN102912760B (en) Lowest navigable water level generating method of downstream river of reservoir
CN114417740B (en) Deep sea breeding situation sensing method
KR20190136681A (en) The supporting method of determination of fouling control in reverse osmosis using classification algorithm
CN102130955B (en) System and method for generating alternative service set of composite service based on collaborative filtering
CN114956360A (en) Sewage treatment aeration oxygenation control method based on hill climbing algorithm
CN116956156A (en) Sewage treatment intelligent aeration method and system based on artificial intelligence

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant