Modular intelligent sewage treatment regulation device and method

Abstract

A modular intelligent sewage treatment regulation device and method, belonging to the technical field of sewage information regulation, obtains the pH value of each sewage pool at each time point in the sampling time interval; obtains the past pH value of each sewage pool at each past time point in the reference time interval; obtains the coherence coefficient of each sewage pool with each other sewage pool; obtains the pH value error amplitude of each sewage pool; obtains the outlier factor of each sewage pool at each time point; obtains multiple approximate spaces of each sewage pool; obtains the outlier amplitude of each sewage pool in each approximate space; performs pH value removal to achieve active sampling of the pH value of sewage in the sewage pool; reduces the error caused by the interaction between sewage pools when sending the pH value to a liquid crystal screen for display; improves the pH value sampling level of sewage in the sewage pool and the treatment level of transmitting the pH value of the sewage in the sewage pool to the LCD screen for display.

Description

Technical Field

[0001] The present invention belongs to the technical field of sewage information regulation, and specifically relates to a modular intelligent sewage treatment regulation device and method. Background Art

[0002] The process of purifying sewage to meet the water quality requirements for discharge into a water body or reuse. Sewage treatment is widely used in various fields such as construction, agriculture, transportation, energy, petrochemicals, environmental protection, urban landscape, medical treatment, catering, etc., and is increasingly entering the daily lives of ordinary people.

[0003] As for sewage treatment for multiple sewage pools, the existing technical solution such as patent publication number "CN204138404U" is often used to perform sewage treatment on multiple sewage pools. Specifically, multiple sewage pools are connected to sewage treatment devices, so that the sewage in the multiple sewage pools flows into the sewage treatment device for sewage treatment.

[0004] On the other hand, during sewage treatment, it is often necessary to perform real-time detection of the pH value of the sewage in the sewage pool. Specifically, corresponding pH meters are installed in multiple sewage pools. The pH meters are connected to the controller, and the controller is also connected to the LCD screen. The pH meter is used to sample the pH value of the corresponding sewage pool and transmit it to the controller. The controller is used to transmit the pH value of the collected sewage in the sewage pool to the LCD screen for display, thereby achieving the function of real-time detection of the pH value of the sewage in the sewage pool.

[0005] During the sampling period, the pH value of the sewage in the sewage pool will be determined by the function of the pH meter due to the scene factors of the sewage pool, causing the components of the pH meter to work unsteadily, which is not conducive to the sampling level of the pH value of the sewage and forms noise values, thereby weakening the accuracy of the pH value sampling; in addition to the noise values ​​caused by the component defects of the pH meter during the sampling period, each sewage pool in the sewage pool scene is often affected by the scene factors of other sewage pools nearby, causing the pH value to fluctuate, resulting in errors in the pH value sampled from the sewage pool, which weakens the level of processing of the pH value of the sewage in the sewage pool that is subsequently transmitted to the LCD screen for display. Summary of the invention

[0006] In order to solve the defects in the prior art, the present invention proposes a modular intelligent sewage treatment adjustment device and method, which obtains the pH value of each sewage pool at each time point in the sampling time interval; obtains the past pH value of each sewage pool at each past time point in the reference time interval; obtains the coherence coefficient of each sewage pool with each other sewage pool; obtains the pH value error amplitude of each sewage pool; obtains the outlier factor of each sewage pool at each time point; obtains multiple approximate spaces of each sewage pool; obtains the outlier amplitude of each sewage pool in each approximate space; performs pH value noise removal to achieve active sampling of the pH value of the sewage in the sewage pool; reduces the error caused by the interaction between sewage pools when sending the pH value to the LCD screen for display; improves the pH value sampling level of the sewage in the sewage pool and the treatment level of transmitting the pH value of the sewage in the sewage pool to the LCD screen for display.

[0007] The present invention uses the following technical solutions.

[0008] A modular intelligent sewage treatment regulation method, comprising:

[0009] The sewage in multiple sewage pools flows to the sewage treatment device for sewage treatment; during the sewage treatment, the pH meter samples the pH value of the corresponding sewage pool and transmits it to the controller, the controller processes the pH value of the sewage collected from the sewage pool, and transmits the pH value of the treated sewage to the LCD screen for display;

[0010] The controller performs a method for treating the pH value of the sewage collected from the sewage pool, comprising:

[0011] Step 1: Obtain the pH value of each sewage pool at each time point in the sampling time interval; obtain the past pH value of each sewage pool at each past time point in the benchmark time interval;

[0012] Step 2: Obtain the correlation coefficient between each sewage pool and each other sewage pool; obtain the pH value error amplitude of each sewage pool;

[0013] Step 3: Obtain the outlier factor of each sewage pool at each time point; obtain multiple approximate spaces of each sewage pool; obtain the outlier amplitude of each sewage pool in each approximate space;

[0014] Step 4: Perform the pH value elimination test to achieve active sampling of the pH value of the sewage in the sewage pool.

[0015] Furthermore, in Step 1, the sampling period, sampling time interval and reference time interval are defined in advance, each time point at a sampling period is a sampling time point of a sampling time interval, and the pH values ​​of all sewage pools at all sampling time points in the sampling time interval are obtained; the past pH values ​​of the sewage pools at each past time point in the reference time interval before the first sampling time point are obtained.

[0016] Furthermore, in Step 1, the sampling period is defined as one second, the sampling interval is five minutes, and the reference interval is thirty minutes.

[0017] Furthermore, Step 2 specifically includes: treating any sewage pool as the current sewage pool, and defining the queue formed by arranging the pH values ​​of all past time points of the current sewage pool according to the chronological order of its sampling time points as the past benchmark queue of the current sewage pool; similarly obtaining the past benchmark queues of all sewage pools; and obtaining the coherence coefficient of the current sewage pool and each other sewage pool based on the coherence of the past pH values ​​of each sewage pool and other sewage pools at all time points.

[0018] Furthermore, the coherence coefficient between the current sewage pool and each other sewage pool is the modulus of the Tanimoto coefficient of the past benchmark queue of the current sewage pool and the past benchmark queue of each other sewage pool.

[0019] Furthermore, Step 2 specifically includes: the pH value error amplitude L of the jth sewage pool j The operational equation is:

[0020]

[0021] In the equation, represents the average of the coherence coefficients between the jth sewage pool and all other sewage pools, Represents the average pH value of all sampling points in the jth sewage pool during the sampling interval, Represents the average of the past pH values ​​of the j-th sewage pool at all past time points in the reference time interval.

[0022] Furthermore, Step 3 specifically includes: defining the number of characteristics in advance, obtaining the time points of the number of characteristics before each time point and defining them as the characteristic time domains of each time point;

[0023] The outlier factor S of the jth sewage pool at time point u j,u The operational equation is:

[0024]

[0025] In the equation, N j,u represents the highest pH value in the characteristic time domain of the jth sewage pool at the uth time point, n j,u represents the minimum pH value of the jth sewage pool at the uth time point in the characteristic time domain, E j,u represents the time point corresponding to the highest pH value in the characteristic time domain of the jth sewage pool at the uth time point, e j ,urepresents the time point corresponding to the lowest pH value of the jth sewage pool at the uth time point in the characteristic time domain, T j,u represents the KL divergence of all pH values ​​in the characteristic time domain of the jth sewage pool at the uth time point;

[0026] Similarly, the outlier factors of all sewage pools at all time points are obtained; for each sewage pool, any time point is regarded as the current time point, and the outlier factor of the current time point minus the outlier factor of the previous time point adjacent to the current time point is defined as the outlier difference of the current time point. Similarly, the outlier difference of each sewage pool at each time point is obtained, and the outlier difference of the first time point is defined as zero.

[0027] Furthermore, Step 3 specifically includes: defining a critical value of distinction in advance, if the outlier distinction between the current time point and the next time point adjacent to the current time point is lower than the critical value of distinction, taking the space formed by the current time point and the next time point adjacent to the current time point as the starting approximate space, taking the average of the outlier distinctions of all time points in the starting approximate space as the global outlier distinction of the starting approximate space, then subtracting the outlier distinction of the next time point adjacent to the starting approximate space from the global outlier distinction of the starting approximate space to obtain the reduction of the outlier distinction, and when the modulus of the reduction of the outlier distinction is lower than the critical value of distinction, adding the next time point adjacent to the starting approximate space to the starting approximate space to obtain a new starting approximate space, until the global outlier distinction of the starting approximate space minus the outlier distinction of the next time point adjacent to the starting approximate space to obtain the reduction of the outlier distinction, and when the modulus of the reduction of the outlier distinction is not lower than the critical value of distinction, the approximate space is obtained; similarly, all the approximate spaces of all sewage pools are obtained.

[0028] Furthermore, Step 3 specifically includes: the outlier amplitude Q of the jth sewage pool in the mth approximate space j,m The operational equation is:

[0029]

[0030] In the equation, L j represents the pH error amplitude of the jth sewage pool, represents the average of the outlier factors of the jth sewage pool at all time points in the mth approximate space;

[0031] Similarly, the outlier amplitudes of all sewage pools in the entire approximate space are obtained.

[0032] Further, Step 4 specifically includes: performing a coordinated clutter removal on the pH value of each sewage pool according to the outlier amplitude of each sewage pool in each approximate space, and obtaining the pH value of each sewage pool after the clutter is removed. The coordinated clutter removal method includes: obtaining the size of each pre-defined convolution kernel and the initial variance of the convolution kernel;

[0033] The adjustment formula difference A of the jth sewage pool in the mth approximate space j,m The operational equation is:

[0034]

[0035] In the equation, A represents the starting variance of the convolution kernel, Q j,m represents the outlier amplitude of the jth sewage pool in the mth approximation space, and e is the Euler number;

[0036] Similarly, the adjustment formula deviation of all sewage pools in all approximate spaces is obtained; the convolution kernel uses the moving average method to remove noise from the pH values ​​of all sewage pools in all approximate spaces according to the size of the convolution kernel and the adjustment formula deviation of each sewage pool in each approximate space, and obtains the pH values ​​of all sewage pools after removing noise; the pH values ​​of all sewage pools after removing noise are regarded as the pH values ​​of the treated sewage, so as to achieve active sampling of the pH value of the sewage in the sewage pool.

[0037] A modular intelligent sewage treatment regulating device, comprising:

[0038] Multiple sewage pools are connected to the sewage treatment device; each of the multiple sewage pools is provided with a corresponding pH meter, which is connected to a controller, which is also connected to a liquid crystal screen. The pH meter is used to sample the pH value of the corresponding sewage pool and transmit it to the controller, which is used to process the pH value of the sewage collected from the sewage pool, and transmit the pH value of the treated sewage to the liquid crystal screen for display;

[0039] The modules running on the controller include:

[0040] The pH value module is used to obtain the pH value of each sewage pool at each time point in the sampling time interval; obtain the past pH value of each sewage pool at each past time point in the reference time interval;

[0041] An error module is used to obtain the correlation coefficient of each sewage pool with each other sewage pool; and obtain the pH value error amplitude of each sewage pool;

[0042] An outlier module is used to obtain the outlier factor of each sewage pool at each time point; obtain multiple approximate spaces of each sewage pool; obtain the outlier amplitude of each sewage pool in each approximate space;

[0043] The cleaning module is used to perform the cleaning of noise values ​​of the pH value, so as to achieve active sampling of the pH value of the sewage in the sewage pool.

[0044] The beneficial effects of the present invention are that, compared with the prior art, the technical effects of the present invention include:

[0045] Through the correlation of the past pH values ​​of each sewage pool and other sewage pools at all time points, the correlation coefficient of each sewage pool and other sewage pools is obtained, and then the error caused by the interaction between the sewage pools is reduced when the pH value is sent to the LCD screen to display the pH value; the average of the past pH values ​​of all past time points is used as a benchmark to reflect the reasonable pH value of the sewage pool scene, combined with the difference between the pH value of each sewage pool and the reasonable pH value, combined with the correlation coefficient, the pH value error amplitude of each sewage pool is obtained, and the pH value error amplitude of each sewage pool is used to reflect the amplitude of the pH value of each sewage pool caused by other sewage pools; according to the pH value of the sewage pool Fluctuation conditions are obtained, and the outlier factors of each sewage pool at each time point are obtained. Based on this, multiple approximate spaces of each sewage pool are obtained according to the reduction of the outlier factors at adjacent time points, and multiple time points represented by the outlier factors are cut into the same approximate space; the outlier factor mean of the approximate space is adjusted according to the pH value error amplitude, and the value after the adjustment is the outlier amplitude of each sewage pool in each approximate space; the pH value is coordinated and noise removal is performed according to the outlier amplitude to remove noise and maximize the accuracy of outliers, thereby improving the pH value sampling level of the sewage in the sewage pool and the treatment level of transmitting the pH value of the sewage in the sewage pool to the LCD screen for display. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 It is a flow chart of the modular intelligent sewage treatment regulation method described in the present invention;

[0047] Figure 2 It is a partial structural diagram of the modular intelligent sewage treatment regulating device described in the present invention. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solution and advantages of the present invention clearer, the following will be combined with the drawings in the embodiments of the present invention to clearly and completely express the technical solution of the present invention. The embodiments expressed in this application are only some embodiments of the present invention, not all embodiments. According to the spirit of the present invention, other embodiments obtained by ordinary technicians in this field without creative work are all within the protection scope of the present invention.

[0049] like Figure 1 As shown, a modular intelligent sewage treatment regulation method according to the present invention comprises:

[0050] The sewage in multiple sewage pools flows to the sewage treatment device for sewage treatment; during the sewage treatment, the pH meter samples the pH value of the corresponding sewage pool and transmits it to the controller, the controller processes the pH value of the sewage collected from the sewage pool, and transmits the pH value of the treated sewage to the LCD screen for display, thereby achieving the function of real-time detection of the pH value of the sewage in the sewage pool;

[0051] The controller performs a method for treating the pH value of the sewage collected from the sewage pool, comprising:

[0052] Step 1: Obtain the pH value of each sewage pool at each time point in the sampling time interval; obtain the past pH value of each sewage pool at each past time point in the benchmark time interval;

[0053] In a preferred but non-limiting embodiment of the present invention, the present invention performs active sampling improvement on the pH value of sewage in a sewage pool based on the pH value, so the pH value in the sewage pool scenario is initially obtained. In Step 1, the sampling period, sampling interval and reference interval are defined in advance, and a plurality of pH values ​​sampled in the sewage pool are obtained by installing a pH meter in different sewage pools. Each time point at a sampling period is a sampling time point of a sampling interval, and the pH values ​​of all sewage pools at all sampling time points in the sampling interval are obtained; the past pH values ​​of the sewage pool at each past time point in the reference interval before the first sampling time point are obtained.

[0054] In a preferred but non-limiting embodiment of the present invention, in Step 1, the present invention defines the sampling period as one second, the sampling interval as five minutes, and the reference interval as thirty minutes.

[0055] Step 2: Obtain the correlation coefficient between each sewage pool and each other sewage pool; obtain the pH value error amplitude of each sewage pool;

[0056] Under the conditions of the sewage pool scene, the pH conditions of different sewage pools often show different degrees of interaction. When the pH value of some sewage pools is not low, the pH value of nearby sewage pools will cause an unstable increase. The correlation coefficient between each sewage pool and other sewage pools is obtained through the correlation of the past pH values ​​of each sewage pool at all time points. The greater the correlation, the higher the correlation coefficient. Because the pH value of each sewage pool in the sewage pool scene is close to a stable value for a long time under reasonable conditions, the reasonable pH value in the sewage pool scene can be reflected by the average of the past pH values ​​of all past time points. The difference in the average pH value at all time points and the reasonable pH value are combined with the correlation coefficient between each sewage pool and other sewage pools to obtain the pH value error amplitude of each sewage pool.

[0057] In a preferred but non-limiting embodiment of the present invention, Step 2 specifically includes: treating any sewage pool as the current sewage pool, and defining the queue formed by arranging the pH values ​​of all past time points of the current sewage pool according to the chronological order of its sampling time points as the past benchmark queue of the current sewage pool; similarly obtaining the past benchmark queues of all sewage pools; and obtaining the coherence coefficient of the current sewage pool and each other sewage pool based on the coherence of the past pH values ​​of each sewage pool and other sewage pools at all time points.

[0058] In a preferred but non-limiting embodiment of the present invention, the coherence coefficient between the current sewage pool and each other sewage pool is the modulus of the Tanimoto coefficient of the past benchmark queue of the current sewage pool and the past benchmark queue of each other sewage pool.

[0059] In a preferred but non-limiting embodiment of the present invention, Step 2 specifically includes: the pH value error amplitude L of the jth sewage pool j The operational equation is:

[0060]

[0061] In the equation, represents the average of the coherence coefficients between the jth sewage pool and all other sewage pools, Represents the average pH value of all sampling points in the jth sewage pool during the sampling interval, Represents the average of the past pH values ​​of the j-th sewage pool at all past time points in the reference time interval.

[0062] Here The modulus represents the value obtained by subtracting the mean of the pH value of the previous period from the mean of the pH value of the jth sewage pool. The higher the value, the further the mean of the pH value of the jth sewage pool is from the reasonable value, and the higher the error amplitude of the pH value of the jth sewage pool. The higher the value of , the greater the impact of the pH value of the j-th sewage pool on other sewage pools, and the higher the pH value error amplitude of the j-th sewage pool; similarly, the pH value error amplitude of all sewage pools is obtained.

[0063] Step 3: Obtain the outlier factor of each sewage pool at each time point; obtain multiple approximate spaces of each sewage pool; obtain the outlier amplitude of each sewage pool in each approximate space;

[0064] For any sewage pool, the outlier factor of the sewage pool at each time point is obtained according to the pH value fluctuation conditions of multiple time points adjacent to the sewage pool before each time point. The higher the fluctuation amplitude and the smaller the time point interval, the greater the fluctuation intensity and the higher the outlier factor. According to the difference in outlier factors between a pair of adjacent time points (the time point is the sampling time point), all time points with similar outlier factors are cut into the same space to obtain multiple spaces with similar representations. Moreover, according to the outlier factors of the sewage pool at all time points in each of the spaces with similar representations combined with the pH value error amplitude of the sewage pool, the outlier amplitude of each of the spaces with similar representations is obtained.

[0065] In a preferred but non-limiting embodiment of the present invention, Step 3 specifically includes: defining the number of characteristics in advance, obtaining the time points of the number of characteristics before each time point (the time point is the sampling time point) and defining them as the characteristic time domain of each time point. The number of characteristics of the present invention can be twenty. In particular, when the time point is not enough for the number of characteristics, the pH value of the corresponding time point in the past time point is used to fill it;

[0066] The outlier factor S of the jth sewage pool at time point u j,u The operational equation is:

[0067]

[0068] In the equation, N j,u represents the highest pH value in the characteristic time domain of the jth sewage pool at the uth time point, n j,u represents the minimum pH value of the jth sewage pool at the uth time point in the characteristic time domain, E j,u represents the time point corresponding to the highest pH value in the characteristic time domain of the jth sewage pool at the uth time point, e j ,u represents the time point corresponding to the lowest pH value of the jth sewage pool at the uth time point in the characteristic time domain, T j,u represents the KL divergence of all pH values ​​in the characteristic time domain of the jth sewage pool at the uth time point; especially in E j,u and e j,u When the corresponding time point is a past time point, it is represented by a number below zero, and the modulus of the number below zero is E j,u or j,u The modulus of the time interval between the corresponding past time point and the first time point, just as the past time point that is one sampling period away from the first time point is defined as the -1th time point;

[0069] Here N j,u -n j,u represents the full range of the pH value of the jth sewage pool in the characteristic time domain at the uth time point. The higher the full range, the higher the fluctuation of the pH value of the jth sewage pool in the characteristic time domain at the uth time point, and the higher the outlier factor of the jth sewage pool at the uth time point; |E j,u -e j,u |Represents the modulus of the pH value of the j-th sewage pool at the u-th time point in the characteristic time domain, which is the maximum value minus the minimum value. The lower the modulus, the more efficient it is for the j-th sewage pool to show a strong fluctuation in the pH value in the characteristic time domain at the u-th time point. Then the outlier factor of the j-th sewage pool at the u-th time point is higher.

[0070] Similarly, the outlier factors of all sewage pools at all time points are obtained; for each sewage pool, any time point is regarded as the current time point, and the outlier factor of the current time point minus the outlier factor of the previous time point adjacent to the current time point is defined as the outlier difference of the current time point. Similarly, the outlier difference of each sewage pool at each time point is obtained, and the outlier difference of the first time point is defined as zero.

[0071] In a preferred but non-limiting embodiment of the present invention, Step 3 specifically also includes: pre-defining a critical value for distinction, if the outlier distinction between the current time point and the next time point adjacent to the current time point is lower than the critical value for distinction, the space formed by the current time point and the next time point adjacent to the current time point is taken as the starting approximate space, the average of the outlier distinctions of all time points in the starting approximate space is taken as the global outlier distinction of the starting approximate space, then the global outlier distinction of the starting approximate space is subtracted from the outlier distinction of the next time point adjacent to the starting approximate space to obtain the reduction of the outlier distinction, and when the modulus of the reduction of the outlier distinction is lower than the critical value for distinction, the next time point adjacent to the starting approximate space is added to the starting approximate space to obtain a new starting approximate space, until the global outlier distinction of the starting approximate space is subtracted from the outlier distinction of the next time point adjacent to the starting approximate space to obtain the reduction of the outlier distinction, and when the modulus of the reduction of the outlier distinction is not lower than the critical value for distinction, the approximate space is obtained; similarly, all the approximate spaces of all sewage pools are obtained.

[0072] In a preferred but non-limiting embodiment of the present invention, Step 3 specifically includes: the outlier amplitude Q of the jth sewage pool in the mth approximate space j,m The operational equation is:

[0073]

[0074] In the equation, L j represents the pH error amplitude of the jth sewage pool, represents the average of the outlier factors of the jth sewage pool at all time points in the mth approximate space;

[0075] Similarly, the outlier amplitudes of all sewage pools in the entire approximate space are obtained.

[0076] Step 4: Perform the pH value elimination test to achieve active sampling of the pH value of the sewage in the sewage pool.

[0077] In a preferred but non-limiting embodiment of the present invention, Step 4 specifically includes: performing a coordinated clutter removal on the pH value of each sewage pool according to the outlier amplitude of each sewage pool in each approximate space, and obtaining the pH value of each sewage pool after the clutter is removed. The method of coordinated clutter removal includes: obtaining the size of each pre-defined convolution kernel and the initial variance of the convolution kernel. The size of the convolution kernel of the present invention can be 5*5, and the initial variance is the highest variance value in principle when the size of the convolution kernel is 5*5;

[0078] The adjustment formula difference A of the jth sewage pool in the mth approximate space j,m The operational equation is:

[0079]

[0080] In the equation, A represents the starting variance of the convolution kernel, Q j,m represents the outlier amplitude of the jth sewage pool in the mth approximation space, and e is the Euler number;

[0081] Here, the approximate space with higher outlier amplitude should maintain the accuracy of outlier value when dispersing, so the variance of the approximate space with high outlier amplitude is reduced, otherwise it is increased;

[0082] Similarly, the adjustment formula deviation of all sewage pools in all approximate spaces is obtained; the convolution kernel uses the moving average method to remove noise from the pH values ​​of all sewage pools in all approximate spaces according to the size of the convolution kernel and the adjustment formula deviation of each sewage pool in each approximate space, and obtains the pH values ​​of all sewage pools after removing noise; the pH values ​​of all sewage pools after removing noise are regarded as the pH values ​​of the treated sewage, so as to achieve active sampling of the pH value of the sewage in the sewage pool.

[0083] like Figure 2 As shown, the modular intelligent sewage treatment regulating device of the present invention comprises:

[0084] Multiple sewage pools are connected to the sewage treatment device, so that the sewage in the multiple sewage pools flows to the sewage treatment device for sewage treatment; multiple sewage pools are equipped with corresponding pH meters, which are connected to the controller, and the controller is also connected to the LCD screen. The pH meter is used to sample the pH value of the corresponding sewage pool and transmit it to the controller. The controller is used to treat the pH value of the sewage collected from the sewage pool, and transmit the pH value of the treated sewage to the LCD screen for display, so as to achieve the function of real-time detection of the pH value of the sewage in the sewage pool;

[0085] The modules running on the controller include:

[0086] The pH value module is used to obtain the pH value of each sewage pool at each time point in the sampling time interval; obtain the past pH value of each sewage pool at each past time point in the reference time interval;

[0087] An error module is used to obtain the correlation coefficient of each sewage pool with each other sewage pool; and obtain the pH value error amplitude of each sewage pool;

[0088] An outlier module is used to obtain the outlier factor of each sewage pool at each time point; obtain multiple approximate spaces of each sewage pool; obtain the outlier amplitude of each sewage pool in each approximate space;

[0089] The cleaning module is used to perform the cleaning of the pH value and achieve active sampling of the pH value of the sewage in the sewage pool. The controller can be a single chip microcomputer or a PLC.

[0090] The beneficial effects of the present invention are that, compared with the prior art, the technical effects of the present invention include:

[0091] Through the correlation of the past pH values ​​of each sewage pool and other sewage pools at all time points, the correlation coefficient of each sewage pool and other sewage pools is obtained, and then the error caused by the interaction between the sewage pools is reduced when the pH value is sent to the LCD screen to display the pH value; the average of the past pH values ​​of all past time points is used as a benchmark to reflect the reasonable pH value of the sewage pool scene, combined with the difference between the pH value of each sewage pool and the reasonable pH value, combined with the correlation coefficient, the pH value error amplitude of each sewage pool is obtained, and the pH value error amplitude of each sewage pool is used to reflect the amplitude of the pH value of each sewage pool caused by other sewage pools; according to the pH value of the sewage pool Fluctuation conditions are obtained, and the outlier factors of each sewage pool at each time point are obtained. Based on this, multiple approximate spaces of each sewage pool are obtained according to the reduction of the outlier factors at adjacent time points, and multiple time points represented by the outlier factors are cut into the same approximate space; the outlier factor mean of the approximate space is adjusted according to the pH value error amplitude, and the value after the adjustment is the outlier amplitude of each sewage pool in each approximate space; the pH value is coordinated and noise removal is performed according to the outlier amplitude to remove noise and maximize the accuracy of outliers, thereby improving the pH value sampling level of the sewage in the sewage pool and the treatment level of transmitting the pH value of the sewage in the sewage pool to the LCD screen for display.

[0092] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents, and any modifications or equivalent replacements that do not deviate from the spirit and scope of the present invention should be covered within the protection space of the claims of the present invention.

Claims

1. A modular intelligent sewage treatment regulation method, characterized in that: include: The sewage in multiple sewage pools flows to the sewage treatment device for sewage treatment; during the sewage treatment, the pH meter samples the pH value of the corresponding sewage pool and transmits it to the controller, the controller processes the pH value of the sewage collected from the sewage pool, and transmits the pH value of the treated sewage to the LCD screen for display; The controller performs a method for treating the pH value of the sewage collected from the sewage pool, comprising: Step 1: Obtain the pH value of each sewage pool at each time point in the sampling time interval; obtain the past pH value of each sewage pool at each past time point in the reference time interval; Step 2: Obtain the correlation coefficient between each sewage pool and each other sewage pool; obtain the pH value error amplitude of each sewage pool; Step 3: Obtain the outlier factor of each sewage pool at each time point; obtain multiple approximate spaces of each sewage pool; obtain the outlier amplitude of each sewage pool in each approximate space; Step 4: Perform pH value elimination to achieve active sampling of pH value of sewage in the sewage pool; Take any sewage pool as the current sewage pool, and define the queue formed by arranging the pH values ​​of all past time points of the current sewage pool according to the order of the sampling time points as the past benchmark queue of the current sewage pool; similarly, obtain the past benchmark queues of all sewage pools; according to the coherence of the past pH values ​​of each sewage pool and other sewage pools at all time points, obtain the coherence coefficient of the current sewage pool and each other sewage pool; The correlation coefficient between the current sewage pool and each other sewage pool is the modulus of the Tanimoto coefficient of the previous reference queue of the current sewage pool and the previous reference queue of each other sewage pool; Step 2 specifically includes: pH value error amplitude L of the jth sewage pool j The operational equation is: In the equation, represents the average of the coherence coefficients between the jth sewage pool and all other sewage pools, Represents the average pH value of all sampling points in the jth sewage pool during the sampling interval, Represents the average of the past pH values ​​of the jth sewage pool at all past time points in the reference time interval; Step 3 specifically includes: defining the number of characteristics in advance, obtaining the time points of the number of characteristics before each time point and defining them as the characteristic time domain of each time point; The outlier factor S of the jth sewage pool at time point u j,u The operational equation is: In the equation, N j,u represents the highest pH value in the characteristic time domain of the jth sewage pool at the uth time point, n j,u represents the lowest pH value in the characteristic time domain of the jth sewage pool at the uth time point, E j,u represents the time point corresponding to the highest pH value in the characteristic time domain of the jth sewage pool at the uth time point, e j,u represents the time point corresponding to the lowest pH value in the characteristic time domain of the jth sewage pool at the uth time point, T j,u represents the KL divergence of all pH values ​​in the characteristic time domain of the jth sewage pool at the uth time point; Similarly, the outlier factors of all sewage pools at all time points are obtained; for each sewage pool, any time point is regarded as the current time point, and the outlier factor of the current time point minus the outlier factor of the previous time point adjacent to the current time point is defined as the outlier difference of the current time point. Similarly, the outlier difference of each sewage pool at each time point is obtained, and the outlier difference of the first time point is defined as zero; Step 3 specifically includes: defining a critical value of distinction in advance, if the outlier distinction between the current time point and the next time point adjacent to the current time point is lower than the critical value of distinction, taking the space formed by the current time point and the next time point adjacent to the current time point as the initial approximate space, taking the average of the outlier distinctions of all time points in the initial approximate space as the global outlier distinction of the initial approximate space, then subtracting the outlier distinction of the next time point adjacent to the initial approximate space from the global outlier distinction of the initial approximate space to obtain the reduction of the outlier distinction, and when the modulus of the reduction of the outlier distinction is lower than the critical value of distinction, adding the next time point adjacent to the initial approximate space to the initial approximate space to obtain a new initial approximate space, until the global outlier distinction of the initial approximate space is subtracted from the outlier distinction of the next time point adjacent to the initial approximate space to obtain the reduction of the outlier distinction, and when the modulus of the reduction of the outlier distinction is not lower than the critical value of distinction, the approximate space is obtained; similarly, all the approximate spaces of all the sewage pools are obtained; Step 3 specifically includes: the outlier amplitude Q of the jth sewage pool in the mth approximate space j,m The operational equation is: In the equation, L j represents the pH error amplitude of the jth sewage pool, represents the average of the outlier factors of the jth sewage pool at all time points in the mth approximate space; Similarly, the outlier amplitudes of all sewage pools in all approximate spaces are obtained; Step 4 specifically includes: according to the outlier amplitude of each sewage pool in each approximate space, performing coordinated clutter removal on the pH value of each sewage pool, and obtaining the pH value of each sewage pool after the clutter is removed. The method of coordinated clutter removal includes: obtaining the size of each pre-defined convolution kernel and the initial variance of the convolution kernel; The adjustment formula difference A of the jth sewage pool in the mth approximate space j,m The operational equation is: In the equation, A represents the starting variance of the convolution kernel, Q j,m represents the outlier amplitude of the jth sewage pool in the mth approximation space, and e is the Euler number; Similarly, the adjustment formula deviation of all sewage pools in all approximate spaces is obtained; the convolution kernel uses the moving average method to remove noise from the pH values ​​of all sewage pools in all approximate spaces according to the size of the convolution kernel and the adjustment formula deviation of each sewage pool in each approximate space, and obtains the pH values ​​of all sewage pools after removing noise; the pH values ​​of all sewage pools after removing noise are used as the pH values ​​of the treated sewage, so as to achieve active sampling of the pH values ​​of the sewage in the sewage pool.

2. The modular intelligent sewage treatment regulation method according to claim 1 is characterized in that: In Step 1, the sampling period, sampling time interval and reference time interval are defined in advance. Each time point from a sampling period is a sampling time point of a sampling time interval. The pH values ​​of all sewage pools at all sampling time points in the sampling time interval are obtained; the past pH values ​​of the sewage pools at each past time point in the reference time interval before the first sampling time point are obtained.

Images