阅读说明：本技术 一种选择水质异常报警监测因子的方法及其系统 (Method and system for selecting water quality abnormity alarm monitoring factor ) 是由 安新国 董雅欠 王正 胡晶泊 于 2021-08-12 设计创作，主要内容包括：本申请公开了一种选择水质异常报警监测因子的方法及其系统,其中选择水质异常报警监测因子的方法,具体包括以下步骤：获取水质监测因子的历史数据；对水质监测因子的历史数据集合进行预处理；根据预处理后的历史数据集合,计算水质监测因子的历史数据集合中任意两个水质监测因子之间的相关指标；根据水质监测因子间的相关指标确定水质监测因子相关性临界值；根据相关性临界值选择满足条件的水质异常报警因子组合。本申请克服了单因子预警无法在水质超标前提前预警；同时通过选择多个相关程度高的水质监测因子组合,组成多因子水质异常报警因子组,依据报警因子监测数据变化趋势,实现对水质超标前的提前预警,提高水质异常报警的灵敏性。(The application discloses a method and a system for selecting a water quality abnormity alarm monitoring factor, wherein the method for selecting the water quality abnormity alarm monitoring factor specifically comprises the following steps: acquiring historical data of a water quality monitoring factor; preprocessing a historical data set of the water quality monitoring factor; according to the preprocessed historical data set, calculating a relevant index between any two water quality monitoring factors in the historical data set of the water quality monitoring factors; determining a correlation critical value of the water quality monitoring factors according to the correlation indexes among the water quality monitoring factors; and selecting the water quality abnormity alarm factor combination meeting the conditions according to the correlation critical value. The method overcomes the defect that single-factor early warning cannot be performed before the water quality exceeds the standard; meanwhile, a multi-factor water quality abnormity alarm factor group is formed by selecting a plurality of water quality monitoring factor combinations with high correlation degrees, and according to the change trend of alarm factor monitoring data, early warning before exceeding the standard of water quality is realized, and the sensitivity of water quality abnormity alarm is improved.)

1. A method for selecting a water quality abnormity alarm monitoring factor is characterized by comprising the following steps:

acquiring a historical data set of water quality monitoring factors;

preprocessing a historical data set of the water quality monitoring factor;

according to the preprocessed historical data set, calculating a relevant index between any two water quality monitoring factors in the historical data set of the water quality monitoring factors;

determining a correlation critical value of the water quality monitoring factors according to the correlation indexes among the water quality monitoring factors;

and selecting a water quality abnormity alarm monitoring factor combination meeting the conditions according to the correlation critical value.

2. The method of claim 1, wherein the historical data set of all water quality monitoring factors is defined as a ═ a_P1，……A_Pb}，A_Pi(i-1, 2.. b) is a historical data set of the water quality monitoring factor Pi.

3. The method of selecting a water quality abnormality alarm monitoring factor of claim 1, further comprising, prior to preprocessing the historical data set of water quality monitoring factors, determining a preprocessed data sequence of water quality monitoring factors.

4. A method of selecting a water quality abnormality alarm monitoring factor according to claim 3, wherein the preprocessing procedure is specifically represented as:

wherein S_pi-cRepresents a normalized value, max (A), of the water quality monitoring factor Pi_Pi)，min(A_Pi) Respectively the maximum value and the minimum value of the historical data of the water quality monitoring factor Pi, c is a natural number ai_c∈A_piThe data represents the c-th data of the historical data set of the water quality monitoring factor Pi.

5. The method of claim 1, wherein the correlation indexes between any two water quality monitoring factors include the correlation degree of any two water quality monitoring factors, the similarity of the historical data change trend of any two water quality monitoring factors, and the data comprehensive correlation degree between any two water quality monitoring factors.

6. The method for selecting the water quality abnormity alarm monitoring factor as claimed in claim 5, wherein the step of calculating the correlation index between any two water quality monitoring factors in the historical data set of the water quality monitoring factor according to the preprocessed historical data set comprises the following substeps:

calculating the correlation degree between any two water quality monitoring factors;

calculating the similarity of the change trends of any two water quality monitoring factors and historical data;

and determining the comprehensive data correlation according to the correlation of any two water quality monitoring factors and the similarity of the historical data change trend.

7. The method of selecting a water quality abnormality alarm monitoring factor according to claim 6, wherein the degree of correlation r_ijThe concrete expression is as follows:

wherein the content of the first and second substances,for pre-processing data sequence S of water quality monitoring factor Pi_piThe average value of (a) of (b),preprocessing data sequence S for water quality monitoring factor Pj_pjK is a natural number, and m is the number of data pieces of each water quality monitoring factor.

8. The method according to claim 6, wherein the water quality is selectedThe method for monitoring the factors for frequent alarm is characterized in that the similarity H of the change trends of the historical data of the correlation between any two water quality monitoring factors Pi and Pj_ijThe concrete expression is as follows:

H_ij＝H_ji＝max[h(S_pi，S_pj)，h(S_pjS_pi)]，j≠i

wherein the content of the first and second substances,a_fifor preprocessing a data sequence S_piIn a sequence of consecutive f numbers, b_fjFor preprocessing a data sequence S_pjIn (2) a sequence of consecutive f numbers,wherein, a_fi-kA pre-processing data sequence S obtained by pre-processing a historical data set representing a water quality monitoring factor Pi_piOf a data sequence of consecutive f numbers, b_fj-kS obtained by preprocessing a historical data set representing a water quality monitoring factor Pj_pjThe kth value of the data sequence of consecutive f numbers in (1); in the same way, the method for preparing the composite material,

9. the method of selecting a water quality abnormality alarm monitoring factor according to claim 6, wherein the data synthesis correlation degree w_ijExpressed as:

whereinH_ijSimilarity alpha and beta representing the change trend of historical data of the correlation between any two water quality monitoring factors Pi and Pj are correlation weight parameters, and alpha + beta is 1 and r is satisfied_ijAnd | represents the absolute value of the correlation between any two water quality monitoring factors Pi and Pj.

10. A system for selecting a water quality abnormity alarm monitoring factor is characterized by specifically comprising: the device comprises an acquisition unit, a preprocessing unit, a calculation unit, a determination unit and a selection unit;

the acquisition unit is used for acquiring a historical data set of the water quality monitoring factor;

the pretreatment unit is used for pretreating the historical data set of the water quality monitoring factors;

the calculation unit is used for calculating the correlation index between any two water quality monitoring factors in the historical data set of the water quality monitoring factors according to the preprocessed historical data set;

the determining unit is used for determining a correlation critical value of the water quality monitoring factor;

and the selection unit is used for selecting the water quality abnormity alarm factors meeting the conditions according to the correlation critical value to form a set of early warning factor groups.

Technical Field

The application relates to the field of data processing, in particular to a method and a system for selecting a water quality abnormity alarm monitoring factor.

Background

The early warning of the water environment quality is the core of the refinement and the scientization of the watershed water environment management. The existing water environment early warning technology is mainly based on real-time data monitoring of a water quality automatic station, and early warning is given to the discovered water quality abnormal phenomenon based on an early warning model. The water environment early warning is divided into single-factor early warning and multi-factor early warning, the single-factor early warning model is based on a single early warning factor, and when monitoring index data exceed an early warning threshold value, water quality warning is carried out; the multi-factor early warning is to select a proper early warning factor combination, analyze the real-time monitoring data relation change of the factor combination through an early warning model, judge whether the data relation of the early warning factor combination is abnormal or not and carry out water quality early warning. The multi-factor early warning realizes early warning before exceeding the standard of water quality by monitoring the combined change trend of a plurality of water quality indexes. The prior art method for determining the combination of the early warning factors generally depends on environmental subject knowledge and experience and is selected by correlation analysis, but the method is too dependent on historical experience, so that the accuracy for determining the early warning factors is poor.

Therefore, how to obtain the early warning factor in a more accurate manner is a problem that needs to be solved urgently by those skilled in the art.

Disclosure of Invention

The application provides a method for selecting a water quality abnormity alarm monitoring factor, which specifically comprises the following steps: acquiring a historical data set of water quality monitoring factors; preprocessing a historical data set of the water quality monitoring factor; according to the preprocessed historical data set, calculating a relevant index between any two water quality monitoring factors in the historical data set of the water quality monitoring factors; determining a correlation critical value of the water quality monitoring factors according to the correlation indexes among the water quality monitoring factors; and selecting the water quality abnormity alarm factor combination meeting the conditions according to the correlation critical value.

The above, wherein the historical data set of all water quality monitoring factors is defined as A ═ { A ═ A_P1，……A_Pb}，A_Pi(i-1, 2.. b) is a historical data set of the water quality monitoring factor Pi.

Before the pre-processing of the historical data set of the water quality monitoring factor, the method further comprises determining a pre-processing data sequence of the water quality monitoring factor.

As above, the preprocessing process is specifically expressed as:m, wherein S is 1,2_pi-cRepresents a normalized value, max (A), of the water quality monitoring factor Pi_Pi)，min(A_Pi) Respectively the maximum value and the minimum value of the historical data of the water quality monitoring factor Pi, c is a natural number ai_c∈A_piThe data represents the c-th data of the historical data set of the water quality monitoring factor Pi.

As above, the correlation indexes between any two water quality monitoring factors include the correlation degree of any two water quality monitoring factors, the similarity of the historical data change trends of any two water quality monitoring factors, and the data comprehensive correlation degree between any two water quality monitoring factors.

As above, wherein the calculating of the correlation index between any two water quality monitoring factors in the historical data set of water quality monitoring factors according to the preprocessed historical data set includes the following substeps: calculating the correlation degree between any two water quality monitoring factors; calculating the similarity of the change trends of any two water quality monitoring factors and historical data; and determining the comprehensive data correlation according to the correlation of any two water quality monitoring factors and the similarity of the historical data change trend.

As above, wherein the degree of correlation r_ijThe concrete expression is as follows:

wherein the content of the first and second substances,for pre-processing data sequence S of water quality monitoring factor Pi_piThe average value of (a) of (b),preprocessing data sequence S for water quality monitoring factor Pj_pjK is a natural number, and m is the number of data pieces of each water quality monitoring factor.

The above, wherein, the similarity H of the historical data change trend of the correlation between any two water quality monitoring factors Pi, Pj_ijThe concrete expression is as follows:

H_ij＝H_ji＝max[h(S_pi，S_pj)，h(S_pjS_pi)]，j≠i

wherein the content of the first and second substances,a_fifor preprocessing a data sequence S_piIn a sequence of consecutive f numbers, b_fjFor preprocessing a data sequence S_pjIn (2) a sequence of consecutive f numbers,wherein, a_fi-kA pre-processing data sequence S obtained by pre-processing a historical data set representing a water quality monitoring factor Pi_piOf a data sequence of consecutive f numbers, b_fj-kS obtained by preprocessing a historical data set representing a water quality monitoring factor Pj_pjThe kth value of the data sequence of consecutive f numbers in (1); in the same way, the method for preparing the composite material,

as above, wherein the data is integrated with the correlation w_ijExpressed as:

whereinH_ijSimilarity alpha and beta representing the change trend of historical data of the correlation between any two water quality monitoring factors Pi and Pj are correlation weight parameters, and alpha + beta is 1 and r is satisfied_ijAnd | represents the absolute value of the correlation between any two water quality monitoring factors Pi and Pj.

A system for selecting a water quality abnormity alarm monitoring factor specifically comprises: the device comprises an acquisition unit, a preprocessing unit, a calculation unit, a determination unit and a selection unit; the acquisition unit is used for acquiring a historical data set of the water quality monitoring factor; the pretreatment unit is used for pretreating the historical data set of the water quality monitoring factors; the calculation unit is used for calculating the correlation index between any two water quality monitoring factors in the historical data set of the water quality monitoring factors according to the preprocessed historical data set; the determining unit is used for determining a correlation critical value of the water quality monitoring factor; and the selection unit is used for selecting the water quality abnormity alarm factors meeting the conditions according to the correlation critical value to form a set of early warning factor groups.

The application has the following beneficial effects:

the method and the system for selecting the water quality abnormity alarm monitoring factor overcome the defect that single-factor early warning cannot be carried out before the water quality exceeds the standard; meanwhile, a multi-factor water quality abnormity alarm factor group is formed by selecting a plurality of water quality monitoring factor combinations with high closeness, and early warning before exceeding the standard of water quality is realized according to the change trend of alarm factor monitoring data, so that the sensitivity of water quality abnormity alarm is improved.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments described in the present application, and other drawings can be obtained by those skilled in the art according to the drawings.

FIG. 1 is a flow chart of a method for selecting a water quality abnormality alarm monitoring factor according to an embodiment of the application;

fig. 2 is an internal structure diagram of a system for selecting a water quality abnormality alarm monitoring factor according to an embodiment of the present application.

Detailed Description

The technical solutions in the embodiments of the present application are clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some, but not all, embodiments of the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.

The application relates to a method and a system for selecting a water quality abnormity alarm factor. According to the method and the device, the intimacy degree between the historical data of the two water quality monitoring factors can be measured, the multi-factor water ecological water quality monitoring factor combination with high intimacy degree is selected as the water quality abnormity alarm factor, and the accuracy of determining the water quality abnormity alarm factor is improved.

Example one

In the embodiment, based on the data correlation and track similarity algorithm, the intimacy degree between any two factors is analyzed dialectically, the 95 percentile algorithm is utilized to calculate the intimacy critical value of the water quality monitoring factor abnormal alarm factor combination, and the water quality monitoring factor of which the intimacy degree between the two factors is greater than the critical value is selected as the multi-factor water quality abnormal alarm factor group.

As shown in fig. 1, the method for selecting a water quality abnormality alarm factor provided by the present application specifically includes the following steps:

step S110: and acquiring a historical data set of the water quality monitoring factor.

Specifically, historical data of the water quality monitoring factors are obtained from the outside and are sorted to form a historical data set. Wherein the historical data set of all water quality monitoring factors is defined as A ═ { A ═ A_P1，……A_PbIn which A is_Pi(i-1, 2.. b) is a historical data set of water quality monitoring factors Pi, a_Pi＝[ai₁，ai₂，……ai_m]，ai_mAnd m is the data number of each water quality monitoring factor.

Step S120: and preprocessing the historical data set of the water quality monitoring factor.

Before the pretreatment, the method also comprises the step of determining a pretreatment data sequence of the water quality monitoring factor Pi, wherein the pretreatment data sequence of the water quality monitoring factor Pi is as follows: s_pi＝[S_pi-1，S_pi-2，……，S_pi-m]。

Specifically, the pretreatment data sequences of all the water quality monitoring factors are processed, specifically normalized, and the data in the pretreatment data sequences of the water quality monitoring factors are mapped into the range of 0-1.

The pretreatment process is specifically represented as:

wherein S_pi-cRepresents a normalized value, max (A), of the water quality monitoring factor Pi_Pi)，min(A_Pi) Respectively the maximum value and the minimum value of the historical data of the water quality monitoring factor Pi, c is a natural number ai_c∈A_piThe data represents the c-th data of the historical data set of the water quality monitoring factor Pi.

Step S130: and calculating the correlation index between any two water quality monitoring factors in the historical data set of the water quality monitoring factors according to the preprocessed historical data set.

Specifically, the correlation index is the correlation of any two water quality monitoring factors, the similarity of the historical data change trends of any two water quality monitoring factors, and the data comprehensive correlation between any two water quality monitoring factors.

The step S130 specifically includes the following sub-steps:

step S1301: and calculating the correlation between any two water quality monitoring factors.

Calculating any two water quality monitorsCorrelation between factors Pi, Pj, where correlation r_ijThe concrete expression is as follows:

wherein the content of the first and second substances,for pre-processing data sequence S of water quality monitoring factor Pi_piThe average value of (a) of (b),preprocessing data sequence S for water quality monitoring factor Pj_pjK is a natural number, and m is the number of data pieces of each water quality monitoring factor.

Further, all the correlation degrees calculated by any two water quality monitoring factors in the historical data set form a correlation degree set R.

Step S1302: and calculating the similarity of the change trends of the historical data of any two water quality monitoring factors.

Specifically, the similarity H of the change trend of the historical data of the correlation degree between any two water quality monitoring factors Pi and Pj_ijThe concrete expression is as follows:

H_ij＝max[h(S_pi,S_pj),h(S_pj,S_pi)],j≠i

wherein the content of the first and second substances,a_fiis a sequence S_piIn a sequence of consecutive f numbers, b_fjIs a sequence S_pjIn (2) a sequence of consecutive f numbers,wherein, a_fi-kS obtained by preprocessing a historical data set representing water quality monitoring factors Pi_piOf a data sequence of consecutive f numbers, b_fj-kRepresenting water quality monitoring factors PjHistorical data set, S obtained after preprocessing_pjOf the data sequence of consecutive f numbers. In the same way, the method for preparing the composite material,

further, the similarity H calculated by any two water quality monitoring factors in the historical data set forms a similarity set G.

Step S1303: and determining the comprehensive data correlation according to the correlation of any two water quality monitoring factors and the similarity of the historical data change trend.

In particular, the data integrated correlation w_ijExpressed as:

whereinH_ijSimilarity alpha and beta representing the change trend of historical data of the correlation between any two water quality monitoring factors Pi and Pj are correlation weight parameters, and alpha + beta is 1 and r is satisfied_ijAnd | represents the absolute value of the correlation between any two water quality monitoring factors Pi, pj.

Further, all the data comprehensive correlations are arranged from small to large to form a data comprehensive correlation set W.

Step S140: and determining a correlation critical value of the water quality monitoring factor according to the correlation index.

Specifically, a water quality monitoring factor correlation critical value is determined according to the data comprehensive correlation set W.

Wherein the correlation critical value c of the water quality monitoring factor is specifically expressed as:

c＝gW[l+2]+(1-g)W[l+1]

e＝(q-1)*0.95

wherein q is the number of elements in the set W, l is the integer part of e, and g is the decimal part of e. W [ l ] is the l-th value of the set W.

Step S150: and selecting the water quality abnormity alarm factor combination meeting the conditions according to the correlation critical value.

Specifically, according to the correlation critical value c of the water quality monitoring factor and the data comprehensive correlation degree set W, a water quality abnormity alarm factor meeting the conditions is selected as a water quality abnormity alarm monitoring factor, specifically, the water quality abnormity alarm monitoring factor is selected according to the following conditions, and a water quality alarm monitoring factor set L is further determined.

L＝{(Pi，Pj)|w_ij＞＝c}

Wherein, w_ijAnd expressing the data comprehensive correlation, and if the data comprehensive correlation between any two water quality monitoring factors Pi and Pj is greater than a correlation critical value, taking the any two water quality monitoring factors as water quality abnormity alarm monitoring factors, otherwise, not taking the any two water quality monitoring factors as the water quality abnormity alarm monitoring factors. And the plurality of water quality abnormity alarm monitoring factors meeting the conditions form a water quality alarm monitoring factor set L.

Example two

As shown in fig. 2, the present application provides a system for selecting a water quality abnormality alarm water quality monitoring factor, which specifically comprises: an acquisition unit 210, a preprocessing unit 220, a calculation unit 230, a determination unit 240, and a selection unit 250.

The obtaining unit 210 is configured to obtain historical data of the water quality monitoring factor.

The preprocessing unit 220 is connected to the obtaining unit 210, and is configured to preprocess the historical data set of the water quality monitoring factor.

The calculating unit 230 is connected to the preprocessing unit 220, and is configured to calculate, according to the preprocessed historical data set, a correlation index between any two water quality monitoring factors in the historical data set of the water quality monitoring factors.

The calculating unit 230 specifically includes the following sub-modules: the device comprises a correlation calculation module, a similarity calculation module and a data comprehensive correlation calculation module.

The correlation degree calculation module is used for calculating the correlation degree between any two water quality monitoring factors.

The similarity calculation module is used for calculating the similarity of the historical data change trends of any two water quality monitoring factors.

And the data comprehensive correlation degree calculation module is connected with the similarity degree calculation module and the correlation degree calculation module and is used for determining the data comprehensive correlation degree according to the correlation degree and the similarity degree of any two water quality monitoring factors.

The determination unit 240 is connected to the calculation unit 230 for determining the correlation threshold of the water quality monitoring factor.

The selecting unit 250 is connected to the determining unit 240, and is configured to select the water quality abnormality alarm factors meeting the conditions according to the correlation critical value, so as to form a set of early warning factor groups.

The application has the following beneficial effects:

the method and the system for selecting the water quality abnormity alarm monitoring factor overcome the defect that single-factor early warning cannot be carried out before the water quality exceeds the standard; meanwhile, a multi-factor water quality abnormity alarm factor group is formed by selecting a plurality of water quality monitoring factor combinations with high closeness, and early warning before exceeding the standard of water quality is realized according to the change trend of alarm factor monitoring data, so that the sensitivity of water quality abnormity alarm is improved.

Although the present application has been described with reference to examples, which are intended to be illustrative only and not to be limiting of the application, changes, additions and/or deletions may be made to the embodiments without departing from the scope of the application.

The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.