A wastewater purification treatment method and system for power transmission and transformation projects based on neural networks

Abstract

The present invention discloses a method and system for purifying wastewater in a power transmission and transformation project based on a neural network. The method includes: detecting the first particle size distribution information and the first near-infrared absorption spectrum of pollutants in the wastewater to be treated; identifying the oil droplet and suspended solid particle sizes of the first particle size distribution information according to the first near-infrared absorption spectrum, the first corresponding relationship between the oil droplet particle size and the wavelength absorption peak, and the second corresponding relationship between the suspended solid particle size and the wavelength absorption peak; determining the purification parameters through a first deep neural network model according to the identified first oil droplet particle size distribution information and the first suspended solid particle size distribution information; controlling the flocculant dosing pump to dose the flocculant according to the target flocculant type and the first dosing amount of the purification parameters, and configuring the pressure parameter of the bubble generator as the pressure parameter corresponding to the first bubble particle size to generate bubbles with the first bubble particle size, so as to realize the purification treatment of the wastewater; the present invention can improve the purification effect of the oil-containing and suspended solid-containing wastewater in the power transmission and transformation project.

Description

Technical Field

[0001] The present invention relates to the technical field of purification treatment, and particularly relates to a method and system for purifying wastewater from a transmission and transformation project based on a neural network. Background Art

[0002] During the implementation of a transmission and transformation project, the wastewater generated during the flushing of mechanical equipment used in the base excavation is rich in high-concentration suspended solids and high-concentration grease, with complex water quality components, high chemical oxygen demand and biochemical oxygen demand, poor oil-water separation performance, large treatment scale, and difficulty in removal. If the wastewater is directly discharged, it will affect the regional water quality and thus have an adverse impact on the ecological environment.

[0003] Flocculants play a key role in the treatment of oily and suspended solid-containing wastewater generated during the implementation of a transmission and transformation project. However, there are many types of flocculants, from low-molecular-weight to high-molecular-weight, from single-type to composite-type; flocculants can be generally divided into two categories: inorganic flocculants and organic flocculants according to their chemical compositions. Among them, inorganic flocculants include inorganic coagulants and inorganic polymer flocculants; organic flocculants include synthetic organic polymer flocculants, natural organic polymer flocculants, and microbial flocculants. Different flocculants have different decontamination effects. The molecular weight and charge density of flocculants will significantly affect the surface charge density of flocs, and thus affect the adhesion of bubbles on the surface of flocs. The strength of the adhesion on the surface of flocs directly determines the decontamination effect of flocculants. At present, for the treatment of oily and suspended solid-containing wastewater generated during the implementation of a transmission and transformation project, mainly a single type of flocculant is put into the wastewater according to a fixed ratio for decontamination, without considering the characteristics of the oily and suspended solid-containing wastewater generated during the implementation of the transmission and transformation project, and the purification effect is poor. Summary of the Invention

[0004] In view of the problems existing in the prior art, an embodiment of the present invention provides a method and system for purifying wastewater from a transmission and transformation project based on a neural network, which can effectively improve the purification effect of oily and suspended solid-containing wastewater generated during the flushing of mechanical equipment in a transmission and transformation project.

[0005] In a first aspect, an embodiment of the present invention provides a method for purifying wastewater from a transmission and transformation project based on a neural network, including:

[0006] Detecting first particle size distribution information of pollutants in the wastewater to be treated in a transmission and transformation project by a laser particle size analyzer;

[0007] Obtaining a first near-infrared absorption spectrum of the wastewater to be treated;

[0008] Based on the first near-infrared absorption spectrum, the first corresponding relationship established in advance between the oil droplet size and the wavelength absorption peak, and the second corresponding relationship between the suspended solid particle size and the wavelength absorption peak, identify the pollutants corresponding to different particle sizes in the first particle size distribution information as oil droplets and suspended solids, and obtain the first oil droplet size distribution information and the first suspended solid particle size distribution information;

[0009] Based on the first oil droplet size distribution information and the first suspended solid particle size distribution information, determine the purification parameters through a pre-established first deep neural network model; wherein, the purification parameters include the type of target flocculant, the first dosage, and the first bubble size;

[0010] Control the flocculant dosing pump to add the corresponding flocculant to the wastewater to be treated according to the type of target flocculant and the first dosage, and configure the pressure parameter of the bubble generator to the pressure parameter corresponding to the first bubble size, so that the bubble generator inputs bubbles with the first bubble size into the wastewater to be treated, so as to purify the wastewater to be treated.

[0011] As an improvement of the above solution, the method further includes:

[0012] Obtain the second near-infrared absorption spectrum in real time during the purification process of the wastewater to be treated;

[0013] Obtain the second particle size distribution information in real time during the purification process of the wastewater to be treated;

[0014] According to the second near-infrared absorption spectrum and the first corresponding relationship between the oil droplet size and the wavelength absorption peak, screen out the particle sizes that match the oil droplet size and the concentration information of the corresponding particle sizes from the second particle size distribution information, and obtain the second oil droplet size distribution information during the purification process of the wastewater to be treated;

[0015] Monitor the bubbles in real time during the purification process of the wastewater to be treated through a high-speed camera, and perform image recognition on the real-time monitored bubble images to obtain the bubble size distribution information during the purification process of the wastewater to be treated;

[0016] Based on the second oil droplet size distribution information and the bubble size distribution information, obtain purification adjustment parameters through a pre-established second deep neural network model; wherein, the purification adjustment parameters include the second dosage of the flocculant corresponding to the type of target flocculant, and the second bubble size;

[0017] Adjust the dosage of the flocculant added by the flocculant dosing pump to the wastewater to be treated according to the second dosage, and control the bubble generator to input bubbles with the second bubble size into the wastewater to be treated, so as to optimize the purification of the wastewater to be treated.

[0018] As an improvement of the above solution, the method further includes:

[0019] Obtaining third near-infrared absorption spectra of multiple samples of oily wastewater containing oil droplets with different particle sizes;

[0020] According to the third near-infrared absorption spectra of different oil droplet particle sizes, determining wavelength absorption peaks corresponding to different oil droplet particle sizes, and establishing a first correspondence relationship between oil droplet particle sizes and wavelength absorption peaks;

[0021] Obtaining fourth near-infrared absorption spectra of multiple samples of suspended solids-containing wastewater containing suspended solids with different particle sizes;

[0022] According to the fourth near-infrared absorption spectra of different suspended solid particle sizes, determining wavelength absorption peaks corresponding to different suspended solid particle sizes, and establishing a second correspondence relationship between suspended solid particle sizes and wavelength absorption peaks.

[0023] As an improvement of the above solution, based on the first near-infrared absorption spectrum, the first correspondence relationship between oil droplet particle sizes and wavelength absorption peaks established in advance, and the second correspondence relationship between suspended solid particle sizes and wavelength absorption peaks, identifying oil droplets and suspended solids for pollutants corresponding to different particle sizes in the first particle size distribution information to obtain a first oil droplet particle size distribution information and a first suspended solid particle size distribution information, including:

[0024] Based on the first near-infrared absorption spectrum and the first correspondence relationship between oil droplet particle sizes and wavelength absorption peaks, obtaining the target oil droplet particle size in the wastewater to be treated;

[0025] Screening out particle sizes matching the target oil droplet particle size and concentration information of the corresponding particle sizes from the first particle size distribution information to obtain the first oil droplet particle size distribution information;

[0026] Based on the first near-infrared absorption spectrum and the second correspondence relationship between suspended solid particle sizes and wavelength absorption peaks, obtaining the target suspended solid particle size in the wastewater to be treated;

[0027] Screening out particle sizes matching the target suspended solid particle size and concentration information of the corresponding particle sizes from the first particle size distribution information to obtain the first suspended solid particle size distribution information.

[0028] As an improvement of the above solution, based on the first oil droplet particle size distribution information and the first suspended solid particle size distribution information, determining purification parameters through a pre-established first deep neural network model, including:

[0029] According to the first oil droplet particle size distribution information and the first suspended solid particle size distribution information, screening out at least one candidate flocculant type from the flocculant database;

[0030] Construct a wastewater feature vector based on the first oil droplet size distribution information, the first suspended solid size distribution information, the current pH value of the wastewater to be treated, and the current water temperature.

[0031] Construct a flocculant feature vector for the corresponding type of at least one candidate flocculant according to the molecular weight and charge density of the flocculant.

[0032] Input the wastewater feature vector and the flocculant feature vectors corresponding to each candidate flocculant type into the first deep neural network model to obtain the floc size change diagrams of the flocculants corresponding to each candidate flocculant type in the wastewater to be treated.

[0033] Determine the purification parameters according to the floc size change diagrams corresponding to each candidate flocculant type.

[0034] As an improvement to the above solution, the determining the purification parameters according to the floc size change diagrams corresponding to each candidate flocculant type includes:

[0035] Calculate the flocculation efficiency and average floc size of the flocculants corresponding to each candidate flocculant type according to the floc size change diagrams corresponding to each candidate flocculant type.

[0036] Select the candidate flocculant type with the highest flocculation efficiency as the target flocculant type.

[0037] Calculate the first dosage of the flocculant corresponding to the target flocculant type according to the flocculation efficiency of the target flocculant type.

[0038] Calculate the first bubble size according to the charge density and average floc size of the flocculant corresponding to the target flocculant type.

[0039] As an improvement to the above solution, the calculating the first bubble size according to the charge density of the flocculant corresponding to the target flocculant type includes:

[0040] Calculate the target bubble attachment degree under the target flocculant type according to the charge density and average floc size of the flocculant corresponding to the target flocculant type.

[0041] Obtain the first bubble size according to the target bubble attachment degree and the pre-established first mapping table between the bubble attachment degree and the bubble size.

[0042] Wherein, configure the pressure parameter of the bubble generator as the pressure parameter corresponding to the first bubble size, so that the bubble generator generates bubbles with the first bubble size.

[0043] As an improvement of the above solution, obtaining the purification adjustment parameters according to the second oil droplet size distribution information and the bubble size distribution information through a pre-established second deep neural network model includes:

[0044] Calculating the oil droplet size distribution width at the current moment according to the second oil droplet size distribution information at the current moment;

[0045] When the oil droplet size distribution width is greater than the preset alarm particle size range, obtaining the purification adjustment parameters according to the second oil droplet size distribution information at the current moment and the bubble size distribution information at the current moment through a pre-established second deep neural network model.

[0046] As an improvement of the above solution, obtaining the purification adjustment parameters according to the second oil droplet size distribution information at the current moment and the bubble size distribution information at the current moment through a pre-established second deep neural network model includes:

[0047] Constructing an oil droplet size distribution feature vector according to the second oil droplet size distribution information at the current moment;

[0048] Constructing a bubble size distribution feature vector according to the bubble size distribution information at the current moment;

[0049] Inputting the oil droplet size distribution feature vector and the bubble size distribution feature vector into the second deep neural network model to obtain the predicted bubble attachment degree;

[0050] Calculating the second bubble diameter and the second dosing amount according to the predicted bubble attachment degree and the target bubble attachment degree.

[0051] In a second aspect, an embodiment of the present invention provides a waste water purification treatment system for a power transmission and transformation project based on a neural network, including:

[0052] A first particle size detection module, configured to detect the first particle size distribution information of pollutants in the waste water to be treated in the power transmission and transformation project through a laser particle size analyzer;

[0053] A first near-infrared absorption spectrum acquisition module, configured to acquire the first near-infrared absorption spectrum of the waste water to be treated;

[0054] A first particle size detection module, configured to detect the first particle size distribution information of pollutants in the waste water to be treated in the power transmission and transformation project through a laser particle size analyzer;

[0055] A first near-infrared absorption spectrum acquisition module, configured to acquire the first near-infrared absorption spectrum of the waste water to be treated;

[0056] The first particle size identification module is configured to identify oil droplets and suspended solids for the pollutants corresponding to different particle sizes in the first particle size distribution information according to the first near-infrared absorption spectrum and the pre-established first correspondence between the oil droplet particle size and the wavelength absorption peak and the second correspondence between the suspended solid particle size and the wavelength absorption peak, so as to obtain the first oil droplet particle size distribution information and the first suspended solid particle size distribution information;

[0057] The purification parameter determination module is configured to determine purification parameters according to the first oil droplet particle size distribution information and the first suspended solid particle size distribution information through a pre-established first deep neural network model; wherein, the purification parameters include the type of target flocculant, the first dosage, and the first bubble particle size;

[0058] The first control module is configured to control the flocculant dosing pump to add the corresponding flocculant to the wastewater to be treated according to the type of target flocculant and the first dosage, and configure the pressure parameter of the bubble generator as the pressure parameter corresponding to the first bubble particle size, so that the bubble generator inputs bubbles with the first bubble particle size into the wastewater to be treated, so as to perform purification treatment on the wastewater to be treated.

[0059] Compared with the prior art, a method and system for purifying wastewater from a power transmission and transformation project based on a neural network according to an embodiment of the present invention detect the first particle size distribution information of pollutants in the wastewater to be treated in a power transmission and transformation project through a laser particle size analyzer, and simultaneously obtain the first near-infrared absorption spectrum of the wastewater to be treated; then, according to the first near-infrared absorption spectrum and the pre-established first correspondence between the oil droplet particle size and the wavelength absorption peak and the second correspondence between the suspended solid particle size and the wavelength absorption peak, identify oil droplets and suspended solids for the pollutants corresponding to different particle sizes in the first particle size distribution information, so as to obtain the first oil droplet particle size distribution information and the first suspended solid particle size distribution information; determine purification parameters according to the first oil droplet particle size distribution information and the first suspended solid particle size distribution information through a pre-established first deep neural network model; finally, control the flocculant dosing pump to add the corresponding flocculant to the wastewater to be treated according to the type of target flocculant and the first dosage indicated by the purification parameters, and at the same time configure the pressure parameter of the bubble generator as the pressure parameter corresponding to the first bubble particle size indicated by the purification parameters, so that the bubble generator inputs bubbles with the first bubble particle size into the wastewater to be treated, and through the combined action of the flocculant and the bubbles, flocculate and float the oil and suspended solids in the wastewater, realize the separation of the oil and suspended solids in the wastewater, and realize the purification treatment of the wastewater to be treated, thereby improving the purification effect of the oil-containing and suspended solid-containing wastewater generated during the flushing process of mechanical equipment in a power transmission and transformation project. Description of the Drawings

[0060] To more clearly illustrate the technical solutions of the present invention, the accompanying drawings to be used in the embodiments will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can be obtained based on these drawings.

[0061] Figure 1 It is a flowchart of a waste water purification treatment method for a power transmission and transformation project based on a neural network provided by an embodiment of the present invention;

[0062] Figure 2 It is a schematic block diagram of a waste water treatment process provided by an embodiment of the present invention;

[0063] Figure 3 It is a schematic flowchart of determining purification parameters provided by an embodiment of the present invention;

[0064] Figure 4 It is a structural block diagram of a waste water purification treatment system for a power transmission and transformation project based on a neural network provided by an embodiment of the present invention. Detailed implementation manners

[0065] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0066] It can be understood that the various numerical numbers involved in the embodiments of the present invention are only for the convenience of description and are not used to limit the scope of the present application. The magnitude of the serial numbers of the processes does not mean the order of execution, and the order of execution of the processes should be determined by their functions and internal logics.

[0067] In the embodiments of the present invention, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. The terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device. Without further limitation, the elements defined by the statement "including..." do not exclude the presence of additional identical elements in the process, method, article or device including the said elements. The term "a plurality of" or "several" means two or more.

[0068] Please refer to Figure 1 , Figure 1 which is a flowchart of a waste water purification treatment method for power transmission and transformation projects based on a neural network provided by an embodiment of the present invention. The waste water purification treatment method for power transmission and transformation projects based on a neural network specifically includes:

[0069] S11: Detect the first particle size distribution information of pollutants in the waste water to be treated in the power transmission and transformation project through a laser particle size detector;

[0070] S12: Obtain the first near-infrared absorption spectrum of the waste water to be treated;

[0071] S13: According to the first near-infrared absorption spectrum, the first corresponding relationship between the oil droplet particle size and the wavelength absorption peak, and the second corresponding relationship between the suspended solid particle size and the wavelength absorption peak established in advance, identify oil droplets and suspended solids for the pollutants corresponding to different particle sizes in the first particle size distribution information, and obtain the first oil droplet particle size distribution information and the first suspended solid particle size distribution information;

[0072] The specific identification process of oil droplets and suspended solids is as follows:

[0073] According to the first near-infrared absorption spectrum and the first corresponding relationship between the oil droplet particle size and the wavelength absorption peak, obtain the target oil droplet particle size in the waste water to be treated;

[0074] Screen out the particle sizes and the concentration information of the corresponding particle sizes that match the target oil droplet particle size from the first particle size distribution information to obtain the first oil droplet particle size distribution information;

[0075] According to the first near-infrared absorption spectrum and the second corresponding relationship between the suspended solid particle size and the wavelength absorption peak, obtain the target suspended solid particle size in the waste water to be treated;

[0076] Screen out the particle sizes and the concentration information of the corresponding particle sizes that match the target suspended solid particle size from the first particle size distribution information to obtain the first suspended solid particle size distribution information.

[0077] S14: According to the first oil droplet particle size distribution information and the first suspended solid particle size distribution information, determine the purification parameters through the first deep neural network model established in advance; wherein, the purification parameters include the type of target flocculant, the first dosage, and the first bubble particle size;

[0078] S15: Control the flocculant dosing pump to dose the corresponding flocculant to the wastewater to be treated according to the target flocculant type and the first dosing amount, and configure the pressure parameter of the bubble generator to the pressure parameter corresponding to the first bubble size, so that the bubble generator inputs bubbles with the first bubble size into the wastewater to be treated, so as to purify the wastewater to be treated.

[0079] It should be noted that the method for purifying wastewater from a power transmission and transformation project based on a neural network according to the embodiments of the present invention can be executed by terminal devices such as a server and a computer equipped with a system for purifying wastewater from a power transmission and transformation project based on a neural network. The system is respectively communicatively connected to a laser particle size analyzer for real-time monitoring of the particle size distribution of pollutants (such as grease and suspended solids) in the wastewater to be treated, and a near-infrared spectrometer for real-time monitoring of the near-infrared absorption spectrum of the wastewater to be treated. At the same time, the system is also communicatively connected to a flocculant dosing pump and a bubble generator, and is used to control the type and dosing amount of the flocculant dosed by the flocculant dosing pump to the wastewater to be treated, and control the pressure parameter of the bubble generator to generate bubbles with a suitable bubble size in the wastewater to be treated. Through the combined action of the flocculant and the bubbles, flocculation and flotation occur in the wastewater, realizing the separation of suspended solids and grease in the wastewater, and realizing the purification treatment of the wastewater to be treated.

[0080] Exemplarily, such as Figure 2As shown, the wastewater to be treated in the power transmission and transformation project can be pumped into the wastewater purification area 2 for storage by the pressure of the transfer pump device 1. Then, the laser particle size detector 3 is started to analyze the particle size of pollutants in the wastewater to be treated in the wastewater purification area, and the first particle size distribution information is obtained and uploaded to the system synchronously. At the same time, the near-infrared spectrometer 4 is started to detect the near-infrared absorption spectrum of the wastewater to be treated, and the first near-infrared absorption spectrum is obtained and uploaded to the system synchronously. After the system receives the first particle size distribution information and the first near-infrared absorption spectrum, it first performs wavelength absorption peak matching analysis on the first near-infrared absorption spectrum according to the first correspondence between the oil droplet particle size and the wavelength absorption peak and the second correspondence between the suspended solid particle size and the wavelength absorption peak stored locally, identifies the particle size and its concentration information matching the oil droplet particle size in the first particle size distribution information, and obtains the first oil droplet particle size distribution information. At the same time, it identifies the particle size and its concentration information matching the suspended solid particle size in the first particle size distribution information, and obtains the first suspended solid particle size distribution information. Then, according to the first oil droplet particle size distribution information and the first suspended solid particle size distribution information, the purification parameters including the type of target flocculant, the first dosage, and the first bubble particle size are determined through the first deep neural network model. Based on the obtained purification parameters, the system controls the flocculant dosing pump 5 arranged in the wastewater purification area to select the flocculant corresponding to the type of target flocculant and dose it into the wastewater to be treated according to the first dosage. At the same time, the pressure parameter of the bubble generator 6 arranged in the wastewater purification area is configured as the pressure parameter corresponding to the first bubble particle size, so that the bubble generator generates bubbles with the first bubble particle size in the wastewater to be treated. Through the combined action of the flocculant and the bubbles, the suspended solids and oils in the wastewater are flocculated and floated, realizing the separation of oils and suspended solids in the wastewater and achieving the purification treatment of the wastewater to be treated. The embodiment of the present invention fully considers the particle size distribution of oils and suspended solids in the oil-containing and suspended solid-containing wastewater generated during the flushing process of mechanical equipment in the power transmission and transformation project, and combines a deep neural network to control the type of flocculant, the dosage, and the bubble particle size, so as to obtain purification parameters adapted to the particle size distribution of oils and suspended solids in the current oil-containing and suspended solid-containing wastewater in the power transmission and transformation project. Compared with the prior art of using a single type of flocculant to be dosed into the wastewater according to a fixed ratio for decontamination, the embodiment of the present invention can effectively improve the purification effect of the oil-containing and suspended solid-containing wastewater generated during the flushing process of mechanical equipment in the power transmission and transformation project.

[0081] Further, the method further includes:

[0082] Obtain the third near-infrared absorption spectra of multiple oil-containing wastewater samples with different oil droplet particle sizes;

[0083] According to the third near-infrared absorption spectra of different oil droplet particle sizes, determine the wavelength absorption peaks corresponding to different oil droplet particle sizes, and establish the first correspondence between the oil droplet particle size and the wavelength absorption peak;

[0084] Obtain the fourth near-infrared absorption spectra of multiple wastewater samples containing suspended solids with different suspended solid particle sizes;

[0085] Based on the fourth near-infrared absorption spectra of different suspended solid particle sizes, determine the wavelength absorption peaks corresponding to different suspended solid particle sizes, and establish a second corresponding relationship between the suspended solid particle sizes and the wavelength absorption peaks.

[0086] In the embodiment of the present invention, a near-infrared spectrum detector is used to scan the oil-containing wastewater sample and the wastewater sample containing suspended solids respectively with near-infrared light waves of 900 to 1700 nm. Then, based on the third near-infrared absorption spectrum of the oil-containing wastewater sample, the system analyzes the wavelength absorption peaks of different oil droplet particle sizes. Oil droplets of different particle sizes have different absorption intensities for light of different wavelengths, and the peak position of the spectrum is positively correlated with the oil droplet particle size; for example, at a wavelength of 1200 nm, oil droplets with a particle size of 20 microns have the strongest absorption peak, and the absorbance reaches 0.85. As the oil droplet particle size decreases, the absorption peak shifts towards the short-wavelength direction. Based on different oil droplet particle sizes and the corresponding wavelength absorption peaks, a first corresponding relationship is established; based on the fourth near-infrared absorption spectrum of the wastewater sample containing suspended solids, the wavelength absorption peaks of different suspended solid particle sizes are analyzed, and similarly, a second corresponding relationship between different suspended solid particle sizes and the corresponding wavelength absorption peaks is established; then, the first corresponding relationship and the second corresponding relationship are stored in the local memory of the server.

[0087] It should be noted that the embodiment of the present invention does not specifically limit the establishment method of the first corresponding relationship and the second corresponding relationship. For example, for the detected different oil droplet particle sizes / suspended solid particle sizes, the maximum and minimum values of the absorption peaks at the central wavelengths of the corresponding oil droplet particle sizes / suspended solid particle sizes under multiple samples can be selected to obtain the value range of the absorption peaks of the corresponding oil droplet particle sizes / suspended solid particle sizes, and based on different oil droplet particle sizes / suspended solid particle sizes and the corresponding value ranges of the absorption peaks, the first corresponding relationship / second corresponding relationship is established; or, the detected different oil droplet particle sizes / suspended solid particle sizes are sorted in ascending order, and then evenly divided into several oil droplet size intervals / suspended solid size intervals. At the same time, the maximum and minimum values of the absorption peaks at the central wavelengths of the corresponding oil droplet size intervals / suspended solid size intervals under multiple samples are selected to obtain the value range of the absorption peaks of the corresponding oil droplet size intervals / suspended solid size intervals, and based on different oil droplet size intervals / suspended solid size intervals and the corresponding value ranges of the absorption peaks, the first corresponding relationship / second corresponding relationship is established.

[0088] As Figure 3 shown, S14: According to the first oil droplet particle size distribution information and the first suspended solid particle size distribution information, determine the purification parameters through a pre-established first deep neural network model, including:

[0089] S141: Screen at least one candidate flocculant type from the flocculant database according to the first oil droplet size distribution information and the first suspended solid size distribution information;

[0090] In the embodiment of the present invention, a flocculant database is established to store different types of flocculants, the molecular weight and charge density of each flocculant, as well as the applicable oil droplet size range and applicable suspended solid size range of each flocculant.

[0091] Before wastewater purification, first, based on the oil droplet sizes in the first oil droplet size distribution information, calculate the width of the oil droplet size distribution in the wastewater to be treated. For example, select the maximum oil droplet size in the first oil droplet size distribution information as the upper limit value and the minimum oil droplet size as the lower limit value to obtain the oil droplet size distribution width; similarly, the width of the suspended solid size distribution in the wastewater to be treated can be calculated.

[0092] Then calculate the first matching degree between the oil droplet size distribution width and the applicable oil droplet size range of each flocculant in the flocculant database. For example, calculate the similarity between the oil droplet size distribution width and the applicable oil droplet size range of each flocculant through the Euclidean distance as the first matching degree between the oil droplet size distribution width and the applicable oil droplet size range of each flocculant; similarly, the second matching degree between the suspended solid size distribution width and the applicable suspended solid size range of each flocculant can be calculated; then select the flocculant types with both the first matching degree and the second matching degree exceeding the preset matching degree threshold as the candidate flocculant types to achieve the preliminary screening of the flocculant.

[0093] S142: Construct a wastewater characteristic vector according to the first oil droplet size distribution information, the first suspended solid size distribution information, the current pH value, and the current water temperature of the wastewater to be treated;

[0094] In the embodiment of the present invention, the current pH value of the wastewater to be treated is detected by a pH meter, and the current water temperature of the wastewater to be treated is detected by a temperature sensor. The system constructs a one-dimensional wastewater characteristic vector based on the oil droplet sizes and corresponding concentration information in the first oil droplet size distribution information, the suspended solid sizes and corresponding concentration information in the first suspended solid size distribution information, the current pH value, and the current water temperature. For example, the wastewater characteristic vector Q = , represents the i-th oil droplet size in the first oil droplet size distribution information, represents the concentration of the i-th oil droplet size in the first oil droplet size distribution information, represents the i-th suspended solid size in the first suspended solid size distribution information, represents the concentration of the i-th suspended solid size in the first suspended solid size distribution information, represents the current pH value of the wastewater to be treated, represents the current water temperature of the wastewater to be treated.

[0095] S143: Construct a flocculant feature vector for the corresponding candidate flocculant type according to the molecular weight and charge density of the flocculant corresponding to at least one candidate flocculant type;

[0096] In the embodiments of the present invention, based on the molecular weight and charge density of the flocculant corresponding to each candidate flocculant type, a one-dimensional flocculant feature vector is constructed. For example, the flocculant feature vector of the j-th candidate flocculant , represents the molecular weight of the j-th candidate flocculant, represents the charge density of the j-th candidate flocculant.

[0097] S144: Input the wastewater feature vector and the flocculant feature vectors corresponding to each candidate flocculant type into the first deep neural network model to obtain the floc size change diagrams of the flocculants corresponding to each candidate flocculant type in the wastewater to be treated.

[0098] It should be understood that during the flocculation process, the floc size distribution changes at all times. Generally speaking, after entering the flocculation stage, the number of small-sized particles decreases rapidly, while the number of large particles increases significantly. The floc size develops from a peak to a low peak. At the same time, due to the aggregation between particles, the range of floc sizes gradually increases, that is, the peak width gradually becomes larger. Based on the above principle, in the embodiments of the present invention, by collecting multiple oil-containing and suspended-solid wastewater samples and recording the characteristic parameters of different oil-containing and suspended-solid wastewater samples, including the oil droplet size distribution, suspended solid size distribution, pH value, water temperature, and the change in the size distribution of flocs in the wastewater samples over time after adding different types of flocculants. Then, at a preset time interval (such as 50 s), select the size distributions at multiple moments after adding the flocculant to the oil-containing and suspended-solid wastewater samples; for the size distribution at each moment, use the floc size in the size distribution as the abscissa and the corresponding particle number as the ordinate to perform curve fitting to obtain the floc size change curve of the corresponding virtual agent; then integrate the floc size change curves of the corresponding virtual agent at multiple moments to generate the floc size change diagram of the corresponding virtual agent.

[0099] The characteristic parameters of the oil-containing and suspended-solid wastewater sample, the molecular weight and charge density of the flocculant input into the oil-containing and suspended-solid wastewater sample are used as model inputs, and the floc size change diagram of the oil-containing and suspended-solid wastewater sample input is used as label data. The first deep neural network model is trained until the preset model accuracy requirement is met, and the trained first deep neural network model is obtained and stored locally in the system for subsequent ready access. It should be noted that the process of training the first deep neural network model belongs to the prior art and will not be elaborated here. Through the model training of the first deep neural network model, the floc size change of the corresponding flocculant under different wastewater environments, flocculant molecular weights, and electric charge densities can be mined, so as to facilitate the candidate screening of the target flocculant type suitable for the current wastewater to be treated.

[0100] In the embodiment of the present invention, the wastewater characteristic vector and the flocculant characteristic vector corresponding to any one of the candidate flocculant types are input into the trained first deep neural network model above to predict the floc size change, and the floc size change diagram of the candidate flocculant type is output.

[0101] Among them, the floc size change diagram records the floc size change curves at different times (such as 50s, 100s, 150s, 200s, 250s, etc. after entering the flocculation stage), and the floc size change curve describes the change trend of the floc size and the number of particles.

[0102] It should be noted that the first deep neural network model can be constructed by neural networks such as convolutional neural network CNN and recurrent neural network RNN, which is not specifically limited in the embodiment of the present invention.

[0103] S145: Determine the purification parameters according to the floc size change diagrams corresponding to each of the candidate flocculant types.

[0104] Specifically, the determining the purification parameters according to the floc size change diagrams corresponding to each of the candidate flocculant types includes:

[0105] Calculate the flocculation efficiency and average floc size of each of the candidate flocculant types according to the floc size change diagrams corresponding to each of the candidate flocculant types;

[0106] Select the candidate flocculant type corresponding to the highest flocculation efficiency as the target flocculant type;

[0107] Calculate the first dosage of the flocculant corresponding to the target flocculant type according to the flocculation efficiency of the target flocculant type;

[0108] Calculate the first bubble size according to the charge density and average floc size of the flocculant corresponding to the target flocculant type.

[0109] Specifically, calculating the first bubble diameter according to the charge density of the flocculant corresponding to the target flocculant type includes:

[0110] Calculating the target bubble attachment degree under the target flocculant type according to the charge density and the average floc diameter of the flocculant corresponding to the target flocculant type;

[0111] Obtaining the first bubble diameter according to the target bubble attachment degree and a pre-established first mapping table between the bubble attachment degree and the bubble particle size;

[0112] Among them, configuring the pressure parameter of the bubble generator as the pressure parameter corresponding to the first bubble diameter, so that the bubble generator generates bubbles with the first bubble diameter.

[0113] Exemplarily, for each candidate flocculant type, for the floc diameter change curve at each moment in its floc diameter change diagram, the floc diameter corresponding to the peak value of the number of particles in all floc diameter change curves is selected, and then the average value of the floc diameters corresponding to the peak values of the number of particles in the floc diameter change curves at all moments is calculated to obtain the average floc diameter of this candidate flocculant type. The functional expression of the average floc diameter is as follows:

[0114] (1);

[0115] Among them, represents the average floc diameter, represents the floc diameter corresponding to the peak value of the number of particles in the floc diameter change curve at the k-th moment in the floc diameter change diagram, represents the total number of floc diameter change curves in the floc diameter change diagram.

[0116] For each candidate flocculant type, for all floc diameter change curves in its floc diameter change diagram, the floc diameter corresponding to the maximum value of the number of particles in all floc diameter change curves is selected, and the flocculation efficiency of this candidate flocculant type is calculated according to the floc diameter corresponding to the maximum value of the number of particles and the initial floc diameter of the corresponding type of candidate flocculant. The functional expression of the flocculation efficiency is as follows:

[0117] 00% (2);

[0118] Among them, represents the flocculation efficiency, represents the floc diameter corresponding to the maximum value of the number of particles in all floc diameter change curves in the floc diameter change diagram, the initial floc diameter of the corresponding type of candidate flocculant, It represents the time length corresponding to the floc diameter change curve corresponding to the maximum number of particles in the floc diameter change diagram from the flocculation start time. In the embodiments of the present invention, the moment when the flocs start to form can be used as the flocculation start time.

[0119] After calculating the flocculation efficiency of each candidate flocculant type, select the candidate flocculant type corresponding to the highest flocculation efficiency as the target flocculant type. Then, based on the flocculation efficiency of the target flocculant type and in combination with the volume of the wastewater to be treated, calculate the first dosage of the flocculant corresponding to the target flocculant type. The functional expression of the first dosage is as follows:

[0120] (3);

[0121] Wherein, represents the first dosage, represents the volume of the wastewater to be treated, represents the desired purification duration, represents the initial particle concentration of the wastewater to be treated, represents the desired particle concentration of the wastewater to be treated. The initial particle concentration of the wastewater to be treated is obtained by calculating the sum of the concentrations of all oil droplet diameters in the first oil droplet diameter distribution information and the sum of the concentrations of all suspended solid diameters in the first suspended solid diameter distribution information. The desired particle concentration of the wastewater to be treated , the desired purification duration can be predefined and is not specifically limited in the embodiments of the present invention.

[0122] In the embodiments of the present invention, it is considered that the molecular weight and charge density of the flocculant will significantly affect the adhesion of bubbles to the surface of the floccules, and the strength of the adhesion directly determines the degree of combination between the bubbles and the floccules. Too strong or too weak adhesion will lead to a decrease in the demulsification efficiency of oil droplets. For example, a flocculant with a high molecular weight is prone to form large-volume and loose-structured floccules, and the surface charge density is relatively low. In this case, the adhesion between the bubbles and the floccules is weak, and the bubbles are easily detached from the surface of the floccules, resulting in incomplete demulsification of the oil droplets; the floccules formed by a flocculant with a low molecular weight are small in volume and compact in structure, with a high surface charge density, strong bubble adhesion, and high oil droplet demulsification efficiency. However, too high a surface charge density will cause the bubbles to agglomerate excessively on the surface of the floccules, forming a dense bubble layer, which hinders the full contact between the oil droplets and the flocculant, and instead reduces the demulsification efficiency. At the same time, the bubble size will also significantly affect the adhesion of bubbles to the surface of the floccules; larger bubbles usually have stronger adhesion due to the larger contact area with the liquid surface or solid particles. Based on this, in the embodiments of the present invention, a matching relationship between the charge density of the flocculant and the bubble diameter is established through an index of the degree of bubble adhesion (the degree of bubble adhesion is used to describe the magnitude of the adhesion (adhesive force) between the bubbles and the surface of the floccules), and an optimal matching point is found to ensure that the combination of a flocculant with a specific charge density and bubbles with a specific bubble size can produce the best flocculation effect, improving the wastewater purification efficiency and purification effect.

[0123] Specifically, by using a high-speed camera to capture the image sequence of the oil droplet flocculation and demulsification process in the oil-containing wastewater sample under the action of flocculants with different charge densities and standard-sized bubbles, and using an image recognition tool to identify the image sequence, the image frame at the start of flocculation and the image frame at the time of demulsification under the action of flocculants with different charge densities are determined, and according to the difference between the time stamp corresponding to the image frame at the start of flocculation and the time stamp corresponding to the image frame at the time of demulsification, the demulsification time of the corresponding flocculant is obtained, and the demulsification times of flocculants with different charge densities are recorded.

[0124] It should be understood that the demulsification time refers to the time required for the emulsion to form and decompose. Since stronger bubble adhesion will make the combination between the bubbles and the liquid surface or solid particles more compact, thus making the emulsion more stable and not easily decomposed, and the demulsification time will be relatively long. Therefore, the greater the degree of bubble adhesion, the longer the demulsification time.

[0125] Then, according to the charge density and demulsification time of the different flocculants recorded above, an association function f( ) between the charge density and the demulsification time is established through a linear regression model.

[0126] After that, according to the association function f( ), calculate the demulsification time at the charge density of the flocculant corresponding to the target flocculant type, and combine the average floc size of the flocculant corresponding to the target flocculant type to calculate the target bubble attachment degree under the target flocculant type. The functional expression of the target bubble attachment degree is as follows:

[0127] (4);

[0128] Among them, represents the target bubble attachment degree, represents the charge density, represents the charge density the demulsification time under, represents the set particle size influence constant, represents the average floc size of the flocculant corresponding to the target flocculant type, 、 represents the weight coefficient, + = 1, this formula describes the relationship between bubble adhesion force and charge density and floc size.

[0129] Finally, according to the target bubble attachment degree, by querying the first mapping table established in advance between the bubble attachment degree and the bubble size, obtain the bubble size corresponding to the target bubble attachment degree as the first bubble size. Similarly, in the embodiment of the present invention, a second mapping table between different bubble sizes and pressure parameters is also established in advance. By querying the second mapping table, the pressure parameter corresponding to the first bubble size can be obtained. Configure the bubble generator with this pressure parameter, and the bubble generator can generate bubbles with the first bubble size.

[0130] In the embodiment of the present invention, the matching relationship between the flocculant charge density and the bubble size is associated through the bubble attachment degree, and the bubble size that best matches the target flocculant type can be found, so as to ensure the best flocculation effect and improve the wastewater purification efficiency and purification effect.

[0131] In an alternative embodiment, the method further includes:

[0132] Obtain the second near-infrared absorption spectrum in real time during the purification process of the wastewater to be treated;

[0133] Obtain the second particle size distribution information in real time during the purification process of the wastewater to be treated;

[0134] According to the second near-infrared absorption spectrum and the first correspondence relationship between the oil droplet particle size and the wavelength absorption peak, screen out the particle size and the concentration information of the corresponding particle size that match the oil droplet particle size from the second particle size distribution information, and obtain the second oil droplet particle size distribution information in the purification process of the wastewater to be treated;

[0135] In an embodiment of the present invention, the second near-infrared absorption spectrum and the second particle size distribution information in the purification process of the wastewater to be treated can be obtained at preset time intervals. It should be noted that the process of obtaining the second oil droplet particle size distribution information can refer to the process of obtaining the first oil droplet particle size distribution information described above, and will not be repeated here.

[0136] The bubbles in the purification process of the wastewater to be treated are monitored in real time by a high-speed camera, and image recognition is performed on the real-time monitored bubble images to obtain the bubble particle size distribution information in the purification process of the wastewater to be treated;

[0137] In an embodiment of the present invention, the bubbles floating in the flocculation stage in the purification process of the wastewater to be treated are monitored in real time by a high-speed camera, continuous frame images within a set time granularity captured by the high-speed camera are obtained at preset time intervals, and the frame image with the highest bubble edge clarity is extracted from the continuous frame images as the bubble image.

[0138] According to the second oil droplet particle size distribution information and the bubble particle size distribution information, purification adjustment parameters are obtained through a pre-established second deep neural network model; wherein, the purification adjustment parameters include the second dosage of the flocculant corresponding to the target flocculant type and the second bubble particle size.

[0139] Specifically, the obtaining of the purification adjustment parameters through the pre-established second deep neural network model according to the second oil droplet particle size distribution information and the bubble particle size distribution information includes:

[0140] According to the second oil droplet particle size distribution information at the current moment, the oil droplet particle size distribution width at the current moment is calculated;

[0141] When the oil droplet particle size distribution width is greater than the preset alarm particle size range, purification adjustment parameters are obtained through the pre-established second deep neural network model according to the second oil droplet particle size distribution information and the bubble particle size distribution information at the current moment.

[0142] Specifically, the obtaining of the purification adjustment parameters through the pre-established second deep neural network model according to the second oil droplet particle size distribution information and the bubble particle size distribution information at the current moment includes:

[0143] According to the second oil droplet particle size distribution information at the current moment, an oil droplet particle size distribution feature vector is constructed;

[0144] According to the bubble particle size distribution information at the current moment, a bubble particle size distribution feature vector is constructed;

[0145] Input the oil droplet size distribution feature vector and the bubble size distribution feature vector into the second deep neural network model to obtain the predicted degree of bubble attachment;

[0146] Calculate the second bubble size and the second dosage according to the predicted degree of bubble attachment and the target degree of bubble attachment.

[0147] Considering that during the wastewater purification process, the particle size of solid suspended matter remains basically unchanged during the flocculation process, while the particle size of oil pollution changes with the flocculation time. Therefore, the embodiments of the present invention mainly consider the changes in the oil droplet size and the bubble size during the flocculation process to dynamically adjust the dosage of the flocculant and the bubble size in the wastewater to be treated.

[0148] Exemplarily, by periodically detecting the second oil droplet size distribution information of the wastewater to be treated during the purification process, then obtaining the maximum oil droplet size and the minimum oil droplet size from the second oil droplet size distribution information detected at the current moment, and determining the oil droplet size distribution width at the current moment with the maximum oil droplet size as the upper limit value and the minimum oil droplet size as the lower limit value. When the oil droplet size distribution width is greater than the preset alarm particle size range, it is determined to dynamically adjust the dosage of the flocculant and the bubble size; otherwise, maintain the current dosage of the flocculant and the bubble size. It should be noted that the present invention does not specifically limit the value of the alarm particle size range. For example, the alarm particle size range can be determined according to a preset error range centered on the oil droplet size distribution width corresponding to the first oil droplet size distribution information. For example, the alarm particle size range = , represents the lower limit value of the oil droplet size distribution width corresponding to the first oil droplet size distribution information, represents the upper limit value of the oil droplet size distribution width corresponding to the first oil droplet size distribution information, represents the preset error value.

[0149] When it is determined that the dosage of the flocculant and the bubble size need to be dynamically adjusted, construct an oil droplet size distribution feature vector based on the second oil droplet size distribution information at the current moment; for example, the oil droplet size distribution feature vector , represents the i-th oil droplet size in the second oil droplet size distribution information, represents the concentration of the i-th oil droplet size in the second oil droplet size distribution information. Similarly, construct a bubble size distribution feature vector according to the bubble size distribution information at the current moment.

[0150] Input the above oil droplet size distribution feature vector and bubble size distribution feature vector into a pre-trained second deep neural network model for predicting the degree of bubble attachment to obtain the predicted degree of bubble attachment. It should be noted that the second deep neural network model can be constructed using a long short-term memory neural network (LSTM), and no specific limitation is set in the embodiments of the present invention. By collecting the oil droplet size distribution information, bubble size distribution information, and the corresponding degree of bubble attachment (the specific calculation can refer to formula (4) above) during the flocculation process under the action of bubbles with different bubble sizes for different wastewater samples as training samples, the long short-term memory neural network (LSTM) is trained to obtain the second deep neural network model. Among them, the training process of the long short-term memory neural network (LSTM) belongs to the prior art and will not be elaborated in detail here.

[0151] By querying the first mapping table established in advance between the degree of bubble attachment and the bubble size, obtain the bubble size corresponding to the predicted degree of bubble attachment as the second bubble size.

[0152] After that, calculate the absolute value of the difference between the predicted degree of bubble attachment and the target degree of bubble attachment. The second dosage of the flocculant corresponding to the target flocculant type , where represents the absolute value of the difference between the predicted degree of bubble attachment and the target degree of bubble attachment, represents a set influence factor. When the predicted degree of bubble attachment is greater than or equal to the target degree of bubble attachment, ; when the predicted degree of bubble attachment is less than the target degree of bubble attachment, . represents a preset constant.

[0153] Adjust the dosage of the corresponding flocculant fed by the flocculant dosing pump to the wastewater to be treated according to the second dosage, and control the bubble generator to input bubbles with the second bubble size to the wastewater to be treated, so as to perform purification and optimization treatment on the wastewater to be treated.

[0154] After calculating the dosage of the flocculant and the bubble size that need to be adjusted, the system controls the flocculant dosing pump to adjust from the first dosage to the second dosage, and at the same time controls the bubble size generated by the bubble generator to adjust from the first bubble size to the second bubble size, so as to periodically and dynamically adjust the dosage of the flocculant and the bubble size according to the actual flocculation effect during the wastewater purification process, and further improve the wastewater purification effect.

[0155] See Figure 4 , Figure 4 FIG. [FIG. number] is a structural block diagram of a wastewater purification treatment system for a transmission and transformation project based on a neural network provided by an embodiment of the present invention. The wastewater purification treatment system for a transmission and transformation project based on a neural network includes:

[0156] The first particle size detection module 11 is used to detect the first particle size distribution information of pollutants in the wastewater to be treated in the power transmission and transformation project through a laser particle size analyzer;

[0157] The first near-infrared absorption spectrum acquisition module 12 is used to acquire the first near-infrared absorption spectrum of the wastewater to be treated;

[0158] The first particle size identification module 13 is used to identify oil droplets and suspended solids for the pollutants corresponding to different particle sizes in the first particle size distribution information according to the first near-infrared absorption spectrum and the pre-established first correspondence between the oil droplet particle size and the wavelength absorption peak and the second correspondence between the suspended solid particle size and the wavelength absorption peak, so as to obtain the first oil droplet particle size distribution information and the first suspended solid particle size distribution information;

[0159] The purification parameter determination module 14 is used to determine the purification parameters according to the first oil droplet particle size distribution information and the first suspended solid particle size distribution information through the pre-established first deep neural network model; wherein, the purification parameters include the type of target flocculant, the first dosage, and the first bubble particle size;

[0160] The first control module 15 is used to control the flocculant dosing pump to add the corresponding flocculant to the wastewater to be treated according to the type of target flocculant and the first dosage, and configure the pressure parameter of the bubble generator to the pressure parameter corresponding to the first bubble particle size, so that the bubble generator inputs bubbles with the first bubble particle size into the wastewater to be treated to purify the wastewater to be treated.

[0161] In an optional embodiment, the system further includes:

[0162] The second near-infrared absorption spectrum acquisition module is used to acquire the second near-infrared absorption spectrum in real time during the purification process of the wastewater to be treated;

[0163] The second particle size detection module is used to acquire the second particle size distribution information in real time during the purification process of the wastewater to be treated;

[0164] The second particle size identification module is used to screen out the particle sizes and the corresponding particle size concentration information that match the oil droplet particle size from the second particle size distribution information according to the second near-infrared absorption spectrum and the first correspondence between the oil droplet particle size and the wavelength absorption peak, so as to obtain the second oil droplet particle size distribution information in the purification process of the wastewater to be treated;

[0165] The bubble monitoring module is used to monitor the bubbles in real time during the purification process of the wastewater to be treated through a high-speed camera, and perform image recognition on the real-time monitored bubble images to obtain the bubble particle size distribution information in the purification process of the wastewater to be treated;

[0166] A purification adjustment parameter determination module, configured to obtain purification adjustment parameters through a pre-established second deep neural network model according to the second oil droplet particle size distribution information and the bubble particle size distribution information; wherein, the purification adjustment parameters include the second dosage of the flocculant corresponding to the target flocculant type and the second bubble particle size.

[0167] A second control module, configured to adjust the dosage of the corresponding flocculant added by the flocculant dosing pump to the wastewater to be treated according to the second dosage, and control the bubble generator to input bubbles with the second bubble particle size into the wastewater to be treated, so as to perform purification and optimization treatment on the wastewater to be treated.

[0168] In an optional embodiment, the system further includes:

[0169] A third near-infrared absorption spectrum acquisition module, configured to acquire third near-infrared absorption spectra of multiple oil-containing wastewater samples with different oil droplet particle sizes.

[0170] A first correspondence establishment module, configured to determine wavelength absorption peaks corresponding to different oil droplet particle sizes according to the third near-infrared absorption spectra of different oil droplet particle sizes, and establish a first correspondence between the oil droplet particle size and the wavelength absorption peak.

[0171] A fourth near-infrared absorption spectrum acquisition module, configured to acquire fourth near-infrared absorption spectra of multiple suspended solid-containing wastewater samples with different suspended solid particle sizes.

[0172] A second correspondence establishment module, configured to determine wavelength absorption peaks corresponding to different suspended solid particle sizes according to the fourth near-infrared absorption spectra of different suspended solid particle sizes, and establish a second correspondence between the suspended solid particle size and the wavelength absorption peak.

[0173] In an optional embodiment, the first particle size identification module 13 includes:

[0174] A target oil droplet particle size determination unit, configured to obtain the target oil droplet particle size in the wastewater to be treated according to the first near-infrared absorption spectrum and the first correspondence between the oil droplet particle size and the wavelength absorption peak.

[0175] An oil droplet particle size distribution information acquisition unit, configured to screen out the particle sizes and the corresponding particle size concentration information that match the target oil droplet particle size from the first particle size distribution information, so as to obtain the first oil droplet particle size distribution information.

[0176] A target suspended solid particle size determination unit, configured to obtain the target suspended solid particle size in the wastewater to be treated according to the first near-infrared absorption spectrum and the second correspondence between the suspended solid particle size and the wavelength absorption peak.

[0177] The suspended solid particle size distribution information acquisition unit is used to screen out the particle sizes and the corresponding concentration information of the particle sizes that match the target suspended solid particle size from the first particle size distribution information, so as to obtain the first suspended solid particle size distribution information.

[0178] In an optional embodiment, the purification parameter determination module 14 includes:

[0179] The flocculant type screening unit is used to screen out at least one candidate flocculant type from the flocculant database according to the first oil droplet particle size distribution information and the first suspended solid particle size distribution information;

[0180] The wastewater characteristic vector construction unit is used to construct a wastewater characteristic vector according to the first oil droplet particle size distribution information, the first suspended solid particle size distribution information, the current pH value and the current water temperature of the wastewater to be treated;

[0181] The flocculant characteristic vector construction unit is used to construct a flocculant characteristic vector of the corresponding candidate flocculant type according to the molecular weight and charge density of the flocculant corresponding to at least one candidate flocculant type;

[0182] The floc particle size change diagram prediction unit is used to input the wastewater characteristic vector and the flocculant characteristic vectors corresponding to each candidate flocculant type into the first deep neural network model to obtain the floc particle size change diagrams of the flocculants corresponding to each candidate flocculant type in the wastewater to be treated;

[0183] The parameter determination unit is used to determine the purification parameters according to the floc particle size change diagrams corresponding to each candidate flocculant type.

[0184] In an optional embodiment, the parameter determination unit includes:

[0185] The flocculation parameter calculation sub-unit is used to calculate the flocculation efficiency and the average floc particle size of each candidate flocculant type according to the floc particle size change diagrams corresponding to each candidate flocculant type;

[0186] The target flocculant type determination sub-unit is used to select the candidate flocculant type corresponding to the highest flocculation efficiency as the target flocculant type;

[0187] The first dosage calculation sub-unit is used to calculate the first dosage of the flocculant corresponding to the target flocculant type according to the flocculation efficiency of the target flocculant type;

[0188] The first bubble particle size calculation sub-unit is used to calculate the first bubble particle size according to the charge density and the average floc particle size of the flocculant corresponding to the target flocculant type.

[0189] In an alternative embodiment, the first bubble size calculation subunit includes:

[0190] A bubble adhesion degree calculation subunit, configured to calculate a target bubble adhesion degree under the target flocculant type according to the charge density and average floc size of the flocculant corresponding to the target flocculant type;

[0191] A query subunit, configured to obtain the first bubble size according to the target bubble adhesion degree and a pre-established first mapping table between the bubble adhesion degree and the bubble size;

[0192] Wherein, the pressure parameter of the bubble generator is configured as the pressure parameter corresponding to the first bubble size, so that the bubble generator generates bubbles with the first bubble size.

[0193] In an alternative embodiment, the purification adjustment parameter determination module includes:

[0194] An oil droplet size distribution width calculation unit, configured to calculate the oil droplet size distribution width at the current moment according to the second oil droplet size distribution information at the current moment;

[0195] A purification adjustment parameter prediction unit, configured to, when the oil droplet size distribution width is greater than a preset alarm particle size range, obtain a purification adjustment parameter through a pre-established second deep neural network model according to the second oil droplet size distribution information and the bubble size distribution information at the current moment.

[0196] In an alternative embodiment, the purification adjustment parameter prediction unit includes:

[0197] An oil droplet size distribution feature vector construction subunit, configured to construct an oil droplet size distribution feature vector according to the second oil droplet size distribution information at the current moment;

[0198] A bubble size distribution feature vector construction subunit, configured to construct a bubble size distribution feature vector according to the bubble size distribution information at the current moment;

[0199] A bubble adhesion degree prediction subunit, configured to input the oil droplet size distribution feature vector and the bubble size distribution feature vector into the second deep neural network model to obtain a predicted bubble adhesion degree;

[0200] A parameter calculation subunit, configured to calculate a second bubble size and a second dosage according to the predicted bubble adhesion degree and the target bubble adhesion degree.

[0201] It should be noted that the working processes of the various modules in the waste water purification treatment system for power transmission and transformation projects based on neural networks described in the embodiments of the present invention can refer to the working processes of the waste water purification treatment method for power transmission and transformation projects based on neural networks described in the above embodiments, and the technical effects achieved are also the same as those of the waste water purification treatment method for power transmission and transformation projects based on neural networks described in the above embodiments, and will not be elaborated here.

[0202] It should be noted that the system embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. In addition, in the attached drawings of the system embodiments provided by the present invention, the connection relationships between the modules indicate that there is a communication connection between them, which can be specifically implemented as one or more communication buses or signal lines. Those of ordinary skill in the art can understand and implement without creative efforts.

[0203] The above is the preferred implementation manner of the present invention. It should be pointed out that for those of ordinary skill in the art in this technical field, without departing from the principle of the present invention, many improvements and refinements can be made, and these improvements and refinements are also regarded as the protection scope of the present invention.

Claims

1. A method for purifying wastewater from power transmission and transformation projects based on neural networks, characterized in that: include: Detecting the first particle size distribution information of pollutants in the wastewater to be treated in the power transmission and transformation project by using a laser particle size detector; Acquiring a first near-infrared absorption spectrum of the wastewater to be treated; According to the first near-infrared absorption spectrum and the pre-established first correspondence between the oil droplet particle size and the wavelength absorption peak, and the pre-established second correspondence between the suspended matter particle size and the wavelength absorption peak, the pollutants corresponding to different particle sizes in the first particle size distribution information are identified as oil droplets and suspended matter, to obtain first oil droplet particle size distribution information and first suspended matter particle size distribution information; According to the first oil droplet particle size distribution information and the first suspended matter particle size distribution information, purification parameters are determined by a pre-established first deep neural network model; wherein the purification parameters include a target flocculant type, a first dosage, and a first bubble particle size; The flocculant dosing pump is controlled to add the corresponding flocculant to the wastewater to be treated according to the target flocculant type and the first dosage, and the pressure parameter of the bubble generator is configured to the pressure parameter corresponding to the first bubble particle size, so that the bubble generator inputs bubbles of the first bubble particle size into the wastewater to be treated to purify the wastewater to be treated.

2. The method for purifying wastewater from power transmission and transformation projects based on a neural network as claimed in claim 1, characterized in that: The method further comprises: Real-time acquisition of a second near-infrared absorption spectrum during the purification process of the wastewater to be treated; Real-time acquisition of second particle size distribution information during the purification process of the wastewater to be treated; According to the second near-infrared absorption spectrum and the first corresponding relationship between the oil droplet diameter and the wavelength absorption peak, the particle diameter matching the oil droplet diameter and the concentration information of the corresponding particle diameter are screened out from the second particle diameter distribution information to obtain the second oil droplet diameter distribution information in the wastewater purification process to be treated; The bubbles in the wastewater to be treated are monitored in real time by a high-speed camera, and the bubble images monitored in real time are recognized to obtain the bubble particle size distribution information in the wastewater to be treated; According to the second oil droplet particle size distribution information and the bubble particle size distribution information, a purification adjustment parameter is obtained through a pre-established second deep neural network model; wherein the purification adjustment parameter includes a second dosage of a flocculant corresponding to a target flocculant type and a second bubble particle size; The flocculant dosing pump is adjusted to add a corresponding flocculant dosage to the wastewater to be treated according to the second dosage, and the bubble generator is controlled to input bubbles of the second bubble size into the wastewater to be treated, so as to purify and optimize the wastewater to be treated.

3. The method for purifying wastewater from power transmission and transformation projects based on neural network according to claim 1, characterized in that: The method further comprises: Obtaining third near-infrared absorption spectra of multiple oily wastewater samples containing different oil droplet sizes; Determine the wavelength absorption peaks corresponding to the different oil droplet sizes according to the third near-infrared absorption spectra of the different oil droplet sizes, and establish a first corresponding relationship between the oil droplet size and the wavelength absorption peak; obtaining fourth near infrared absorption spectra of a plurality of suspended matter wastewater samples having different suspended matter particle sizes; According to the fourth near-infrared absorption spectra of different suspended matter particle sizes, wavelength absorption peaks corresponding to different suspended matter particle sizes are determined, and a second corresponding relationship between the suspended matter particle size and the wavelength absorption peak is established.

4. The method for purifying wastewater from power transmission and transformation projects based on a neural network as claimed in claim 3, characterized in that: According to the first near-infrared absorption spectrum and the pre-established first correspondence between the oil droplet particle size and the wavelength absorption peak, and the pre-established second correspondence between the suspended matter particle size and the wavelength absorption peak, the pollutants corresponding to different particle sizes in the first particle size distribution information are identified with oil droplets and suspended matter to obtain the first oil droplet particle size distribution information and the first suspended matter particle size distribution information, including: According to the first near-infrared absorption spectrum and the first corresponding relationship between the oil droplet diameter and the wavelength absorption peak, the target oil droplet diameter in the wastewater to be treated is obtained; Screening out the particle size matching the target oil droplet particle size and the concentration information of the corresponding particle size from the first particle size distribution information to obtain the first oil droplet particle size distribution information; According to the first near-infrared absorption spectrum and a second corresponding relationship between the suspended matter particle size and the wavelength absorption peak, the target suspended matter particle size in the wastewater to be treated is obtained; The particle size matching the target suspended matter particle size and the concentration information of the corresponding particle size are screened out from the first particle size distribution information to obtain the first suspended matter particle size distribution information.

5. The method for purifying wastewater from power transmission and transformation projects based on neural network according to claim 1, characterized in that: The step of determining purification parameters according to the first oil droplet particle size distribution information and the first suspended matter particle size distribution information by using a pre-established first deep neural network model includes: Screening out at least one candidate flocculant type from a flocculant database according to the first oil droplet particle size distribution information and the first suspended matter particle size distribution information; Constructing a wastewater feature vector according to the first oil droplet particle size distribution information, the first suspended matter particle size distribution information, and the current pH value and current water temperature of the wastewater to be treated; According to the molecular weight and charge density of the flocculant corresponding to at least one candidate flocculant type, construct a flocculant feature vector of the corresponding candidate flocculant type; Inputting the wastewater feature vector and the flocculant feature vectors corresponding to each of the candidate flocculant types into the first deep neural network model to obtain a flocculant particle size change graph of the flocculant corresponding to each of the candidate flocculant types in the wastewater to be treated; The purification parameters are determined according to the flocculent particle size variation diagram corresponding to each of the candidate flocculant types.

6. The method for purifying wastewater from power transmission and transformation projects based on a neural network as claimed in claim 5, characterized in that: The step of determining the purification parameters according to the flocculant particle size variation diagram corresponding to each candidate flocculant type includes: Calculating the flocculation efficiency and average flocculent particle size of each candidate flocculant type according to the flocculent particle size change diagram corresponding to each candidate flocculant type; Select the candidate flocculant type corresponding to the highest flocculation efficiency as the target flocculant type; Calculating a first dosage of a flocculant corresponding to the target flocculant type according to the flocculation efficiency of the target flocculant type; The first bubble particle size is calculated according to the charge density of the flocculant corresponding to the target flocculant type and the average flocculent particle size.

7. The method for purifying wastewater from power transmission and transformation projects based on a neural network as claimed in claim 6, characterized in that: The calculating the first bubble particle size according to the charge density of the flocculant corresponding to the target flocculant type includes: Calculating a target bubble attachment degree under the target flocculant type according to the charge density and average flocculent particle size of the flocculant corresponding to the target flocculant type; The first bubble particle size is obtained according to the target bubble adhesion degree and a pre-established first mapping table between the bubble adhesion degree and the bubble particle size.

8. The method for purifying wastewater from power transmission and transformation projects based on a neural network as claimed in claim 2, characterized in that: The step of obtaining purification adjustment parameters according to the second oil droplet size distribution information and the bubble size distribution information by using a pre-established second deep neural network model includes: Calculating the oil droplet size distribution width at the current moment according to the second oil droplet size distribution information at the current moment; When the oil droplet particle size distribution width is greater than the preset alarm particle size range, the purification adjustment parameters are obtained according to the second oil droplet particle size distribution information at the current moment and the bubble particle size distribution information at the current moment through a pre-established second deep neural network model.

9. The method for purifying wastewater from power transmission and transformation projects based on a neural network as claimed in claim 8, characterized in that: The purification adjustment parameters are obtained by using a pre-established second deep neural network model according to the second oil droplet particle size distribution information at the current moment and the bubble particle size distribution information at the current moment, including: Constructing an oil droplet size distribution feature vector according to the second oil droplet size distribution information at the current moment; According to the bubble particle size distribution information at the current moment, a bubble particle size distribution feature vector is constructed; Inputting the oil droplet size distribution feature vector and the bubble size distribution feature vector into the second deep neural network model to obtain a predicted bubble adhesion degree; According to the predicted bubble adhesion degree and the target bubble adhesion degree, a second bubble particle size and a second dosage are calculated.

10. A power transmission and transformation engineering wastewater purification system based on neural network, characterized in that: include: A first particle size detection module is used to detect first particle size distribution information of pollutants in wastewater to be treated in a power transmission and transformation project through a laser particle size detector; A first near-infrared absorption spectrum acquisition module, used to acquire a first near-infrared absorption spectrum of the wastewater to be treated; a first particle size identification module, for identifying oil droplets and suspended matter for pollutants corresponding to different particle sizes in the first particle size distribution information according to the first near-infrared absorption spectrum and a pre-established first correspondence between oil droplet particle size and wavelength absorption peak, and a pre-established second correspondence between suspended matter particle size and wavelength absorption peak, to obtain first oil droplet particle size distribution information and first suspended matter particle size distribution information; A purification parameter determination module, used to determine purification parameters according to the first oil droplet particle size distribution information and the first suspended matter particle size distribution information through a pre-established first deep neural network model; wherein the purification parameters include a target flocculant type, a first dosage, and a first bubble particle size; The first control module is used to control the flocculant dosing pump to add the corresponding flocculant to the wastewater to be treated according to the target flocculant type and the first dosage, and configure the pressure parameter of the bubble generator to the pressure parameter corresponding to the first bubble particle size, so that the bubble generator inputs bubbles of the first bubble particle size into the wastewater to be treated to purify the wastewater to be treated.

Images