CN113702609A - Water quality detection method and system - Google Patents
Water quality detection method and system Download PDFInfo
- Publication number
- CN113702609A CN113702609A CN202110998159.7A CN202110998159A CN113702609A CN 113702609 A CN113702609 A CN 113702609A CN 202110998159 A CN202110998159 A CN 202110998159A CN 113702609 A CN113702609 A CN 113702609A
- Authority
- CN
- China
- Prior art keywords
- water quality
- grade
- data
- detection data
- evaluation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 331
- 238000001514 detection method Methods 0.000 title claims abstract description 97
- 238000011156 evaluation Methods 0.000 claims abstract description 62
- 238000000034 method Methods 0.000 claims abstract description 58
- 238000013441 quality evaluation Methods 0.000 claims abstract description 41
- 238000010219 correlation analysis Methods 0.000 claims abstract description 34
- 238000005259 measurement Methods 0.000 claims abstract description 13
- 238000004364 calculation method Methods 0.000 claims description 20
- 239000011159 matrix material Substances 0.000 claims description 12
- XKMRRTOUMJRJIA-UHFFFAOYSA-N ammonia nh3 Chemical compound N.N XKMRRTOUMJRJIA-UHFFFAOYSA-N 0.000 claims description 11
- OAICVXFJPJFONN-UHFFFAOYSA-N Phosphorus Chemical compound [P] OAICVXFJPJFONN-UHFFFAOYSA-N 0.000 claims description 10
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 10
- 229910052760 oxygen Inorganic materials 0.000 claims description 10
- 239000001301 oxygen Substances 0.000 claims description 10
- 229910052698 phosphorus Inorganic materials 0.000 claims description 10
- 239000011574 phosphorus Substances 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 10
- UCKMPCXJQFINFW-UHFFFAOYSA-N Sulphide Chemical compound [S-2] UCKMPCXJQFINFW-UHFFFAOYSA-N 0.000 claims description 8
- ISWSIDIOOBJBQZ-UHFFFAOYSA-N Phenol Chemical compound OC1=CC=CC=C1 ISWSIDIOOBJBQZ-UHFFFAOYSA-N 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 5
- 238000012163 sequencing technique Methods 0.000 claims description 5
- 238000005070 sampling Methods 0.000 claims description 4
- 238000012854 evaluation process Methods 0.000 abstract description 4
- 230000004044 response Effects 0.000 abstract description 3
- 238000004458 analytical method Methods 0.000 description 10
- 230000008569 process Effects 0.000 description 9
- 239000010865 sewage Substances 0.000 description 5
- 230000009466 transformation Effects 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 3
- -1 permanganate index Chemical compound 0.000 description 3
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 150000002989 phenols Chemical class 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 239000003599 detergent Substances 0.000 description 1
- 239000010791 domestic waste Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 210000003608 fece Anatomy 0.000 description 1
- 239000003673 groundwater Substances 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 229910052757 nitrogen Inorganic materials 0.000 description 1
- 239000000618 nitrogen fertilizer Substances 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 239000002686 phosphate fertilizer Substances 0.000 description 1
- 244000144977 poultry Species 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 238000004451 qualitative analysis Methods 0.000 description 1
- 238000001303 quality assessment method Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 239000002352 surface water Substances 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/18—Water
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/11—Complex mathematical operations for solving equations, e.g. nonlinear equations, general mathematical optimization problems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A20/00—Water conservation; Efficient water supply; Efficient water use
- Y02A20/152—Water filtration
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Theoretical Computer Science (AREA)
- Pure & Applied Mathematics (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Algebra (AREA)
- General Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Chemical & Material Sciences (AREA)
- Health & Medical Sciences (AREA)
- Food Science & Technology (AREA)
- Computing Systems (AREA)
- Operations Research (AREA)
- Medicinal Chemistry (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Or Analyzing Non-Biological Materials By The Use Of Chemical Means (AREA)
Abstract
The invention discloses a water quality detection method, which comprises the following steps: obtaining historical water quality detection data to construct a water quality grade example library; acquiring actual measurement data corresponding to each water quality evaluation factor of a water quality sample to be detected; extracting water quality examples having the same water quality environment as the water quality samples to be detected from the water quality grade example library, and respectively calculating the overall similarity of the actually measured data corresponding to the water quality samples and the historical detection data of each water quality example; if the overall similarity corresponding to each water quality example is smaller than a preset threshold value, detecting a water quality sample by adopting a grey correlation analysis method; otherwise, selecting the water quality grade corresponding to the water quality example with the maximum overall similarity from the water quality examples with the overall similarity larger than the preset threshold value as the detection result of the water quality sample. According to the method, the grey correlation analysis method and the example reasoning method are combined, so that the evaluation process is more convenient, the evaluation response speed is reduced, and the cost is saved.
Description
Technical Field
The invention belongs to the technical field of water quality detection and analysis, and particularly relates to a water quality detection method and system.
Background
Water is a source of life, is a prerequisite for life to survive and is also a necessary condition for promoting economic development. However, in recent years, with the continuous development of economy, people have the phenomena of less treatment, disordered treatment or even no treatment in the process of treating domestic, industrial and agricultural sewage, and the quality of water resources in China is continuously reduced. In order to better manage and maintain water resources, reasonable analysis and evaluation on water quality are needed, and only then can a scientific and reasonable transformation plan be made and effective measures be taken.
At present, the commonly used methods for detecting and analyzing water quality mainly include: analytic hierarchy process, fuzzy evaluation process, single index evaluation process, pollution index process, gray evaluation process, etc. The determination subjectivity of the analytic hierarchy process weight coefficient is strong; the fuzzy evaluation method is relatively complex in calculation and not clear enough in concept; the single index evaluation method is too conservative, and the objectivity of the evaluation result cannot be guaranteed; the pollution index method can judge whether the comprehensive water quality reaches the standard but cannot judge the water quality category. The grey correlation analysis method analyzes the correlation degree among all factors according to sequence comparability and similarity, has no specific requirements on the size and irregularity of a sample in water quality evaluation, and does not cause the situation that a quantitative result does not accord with a qualitative analysis result, so the grey correlation analysis method has extremely high utilization rate in water quality evaluation work. However, the gray correlation analysis method is complex in calculation, and if the gray correlation analysis is performed once every time a sample is taken, the time and cost are undoubtedly great loss.
Disclosure of Invention
Aiming at least one defect or improvement requirement in the prior art, the invention provides a water quality detection method and a water quality detection system, and aims to solve the problems of complex calculation degree, high cost and the like of water quality detection based on a grey correlation analysis method in the prior art.
To achieve the above object, according to one aspect of the present invention, there is provided a water quality detecting method, the method including:
obtaining historical water quality detection data to construct a water quality grade case base, wherein the historical detection data of water quality cases under different water quality environments and corresponding water quality grades are stored in the water quality grade case base; the historical detection data comprises at least one water quality evaluation factor;
acquiring actual measurement data corresponding to each water quality evaluation factor of a water quality sample to be detected;
extracting water quality examples having the same water quality environment as the water quality samples to be detected from the water quality grade example library, and respectively carrying out similarity calculation on the actually measured data corresponding to the water quality samples and the historical detection data of each water quality example to obtain the overall similarity between the actually measured data of the water quality samples and the historical detection data of the water quality examples;
if the overall similarity corresponding to each water quality example is smaller than a preset threshold value, detecting a water quality sample by adopting a grey correlation analysis method; otherwise, selecting the water quality grade corresponding to the water quality example with the maximum overall similarity from the water quality examples with the overall similarity larger than the preset threshold value as the detection result of the water quality sample.
Preferably, the acquiring of the historical water quality detection data to construct the water quality grade example library includes:
acquiring historical detection data of water quality samples of a plurality of different sampling points under each water quality environment;
and analyzing the historical detection data by using a grey correlation analysis method to obtain the water quality grades corresponding to the water quality evaluation factors in the historical detection data, and generating a water quality grade example library.
Preferably, the calculating the similarity between the measured data corresponding to the water quality sample and the historical detection data of each water quality example respectively to obtain the overall similarity between the measured data of the water quality sample and the historical detection data of the water quality example comprises:
respectively calculating the local similarity between the actually measured data corresponding to the water quality sample and each water quality evaluation factor in the historical detection data of each water quality example;
and calculating the overall similarity between the measured data and the examples according to the local similarity of each water quality evaluation factor and the weight occupied by each water quality evaluation factor.
Preferably, the calculation formula of the local similarity is as follows:
overall similarity (simk (m, n))allThe calculation formula of (a) is as follows:
the simk (m, n) represents the local similarity of the actually measured data m and the instance n in the instance library on the same evaluation factor k, Δ r represents the difference between the maximum value and the minimum value of the evaluation factor k in the range degree of each grade, and Δ d is the absolute value of the difference between the k value in the actually measured data m and the k value in the instance n; l represents the number of water quality evaluation factors; (simk (m, n))allRepresenting the overall similarity of the measured data m and the example n in the example library on the l evaluation factors, and w (k) representing the weight occupied by the evaluation factor k.
Preferably, if the overall similarity corresponding to each water quality example is smaller than a preset threshold, the detecting the water quality sample by using a gray correlation analysis method includes:
taking the measured data of the water quality sample to be detected as a reference sequence, taking the water quality grade standard data as a reference sequence, constructing a grey correlation analysis matrix B,
wherein xiAnd (3) representing the corresponding historical detection data when the water quality standard grade is i, and l represents the number of evaluation factors.
Preferably, the method further comprises the following steps: carrying out dimensionless treatment on the actual measurement data of the water quality sample to be detected and the historical detection data of the water quality sample to obtain a matrix D,
wherein y isiA value y obtained by non-dimensionalizing the corresponding historical detection data when the standard grade of the water quality is i0The number of the evaluation factors is represented by l, which is a value obtained by subjecting measured data to non-dimensionalization processing.
Preferably, the method further comprises:
and calculating a correlation coefficient and a correlation degree according to the reference sequence and the comparison sequence after the non-dimensionalization processing, sequencing the correlation degrees, and taking the water quality grade corresponding to the comparison sequence with the maximum correlation degree after the sequencing as a detection result.
Preferably, the water quality evaluation factors comprise volatile phenol, biochemical oxygen demand, ammonia nitrogen, total phosphorus and sulfide.
According to a second aspect of the present invention, there is also provided a water quality detecting system, comprising:
the water quality grade real-time storage system comprises a real-time storage module, a real-time storage module and a real-time storage module, wherein the real-time storage module is used for acquiring historical water quality detection data to construct a water quality grade real-time storage, and the water quality grade real-time storage stores the historical detection data of water quality examples under different water quality environments and corresponding water quality grades; the historical detection data comprises at least one water quality evaluation factor;
the data acquisition module is used for acquiring actual measurement data corresponding to each water quality evaluation factor of the water quality sample to be detected;
the calculation module is used for extracting water quality examples with the same water quality environment as the water quality samples to be detected from the water quality grade example library, and respectively carrying out similarity calculation on the measured data corresponding to the water quality samples and the historical detection data of each water quality example to obtain the overall similarity between the measured data of the water quality samples and the historical detection data of the water quality examples;
the evaluation module is used for detecting the water quality samples by adopting a grey correlation analysis method if the overall similarity corresponding to each water quality example is smaller than a preset threshold value; otherwise, selecting the water quality grade corresponding to the water quality example with the maximum overall similarity from the water quality examples with the overall similarity larger than the preset threshold value as the detection result of the water quality sample.
According to a third aspect of the present invention, there is also provided a computer readable medium storing a computer program executable by an electronic device, the computer program, when run on the electronic device, causing the electronic device to perform the steps of any of the methods described above.
In general, compared with the prior art, the above technical solution contemplated by the present invention can achieve the following beneficial effects:
according to the water quality detection method and system provided by the invention, the water quality grade example library is constructed by acquiring historical water quality detection data; acquiring actual measurement data corresponding to each water quality evaluation factor of a water quality sample to be detected; extracting water quality examples having the same water quality environment as the water quality samples to be detected from the water quality grade example library, and respectively carrying out similarity calculation on the actually measured data corresponding to the water quality samples and the historical detection data of each water quality example to obtain the overall similarity between the actually measured data of the water quality samples and the historical detection data of the water quality examples; if the overall similarity corresponding to each water quality example is smaller than a preset threshold value, detecting a water quality sample by adopting a grey correlation analysis method; otherwise, selecting the water quality grade corresponding to the water quality example with the maximum overall similarity from the water quality examples with the overall similarity larger than the preset threshold value as the detection result of the water quality sample. Compared with the traditional water quality evaluation method, the method combines the grey correlation analysis method with the example reasoning method, is more efficient and practical, reduces the evaluation response speed and saves the cost.
Drawings
FIG. 1 is a schematic flow chart of a water quality detection method according to an embodiment of the present invention;
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. In addition, the technical features involved in the embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
The method has the main innovation points that on the basis of a grey correlation analysis method, CBR (Case-Based analysis) is combined, namely, an existing example in an example library is used as a reference, the overall similarity between the actually measured data of the water quality sample to be detected and the historical detection data in the example library is carried out, whether the subsequent grey correlation analysis is carried out on the data to be evaluated is determined by comparing whether the overall similarity exceeds a preset threshold value, so that the flow of water quality detection and analysis is simplified, the intellectualization and the dynamization of the water quality detection and analysis are realized by using the accuracy of the grey correlation analysis method and the high efficiency of the example inference, the decision cost of water conservancy related personnel is reduced, the accuracy of the detection and analysis is improved, and the response speed of the detection and analysis is reduced.
Fig. 1 is a schematic flow chart of a water quality detection method provided in this embodiment, and referring to fig. 1, in this embodiment, the method includes the following steps:
s101: obtaining historical water quality detection data to construct a water quality grade case base, wherein the historical detection data of water quality cases under different water quality environments and corresponding water quality grades are stored in the water quality grade case base; the historical detection data comprises at least one water quality evaluation factor;
in this embodiment, the water quality class case stores measured values of different evaluation factors in different water quality environments such as rivers and lakes and corresponding water quality classes, and the water quality evaluation result is obtained by constructing the water quality class case for performing similarity reasoning on water quality data to be evaluated.
Specifically, the water quality evaluation factor refers to an index for evaluating the water quality, and the evaluation factor needs to be considered in combination with the actual measurement data of the water quality and the local water quality condition, and the invention is not particularly limited; common evaluation factors include dissolved oxygen, permanganate index, sulfide, ammonia nitrogen, total phosphorus, and the like. In this example, five evaluation factors of volatile phenol, biochemical oxygen demand, ammonia nitrogen, total phosphorus and sulfide are selected for illustration.
In this embodiment, the water quality evaluation grade refers to the water quality evaluation grade of the groundwater quality standard issued by the country, and the water quality grade is divided into five grades, and the numerical range of the evaluation factor corresponding to each grade is specifically shown in the following table:
TABLE 1 quality standard water quality evaluation grade of surface water environment
The method comprises the following steps of firstly, constructing a water quality evaluation grade example library, wherein a large number of examples are required, specifically, the examples can be obtained from data provided by an existing official platform such as a water conservancy bureau and the like, and can also be constructed according to a large number of sampling samples.
In one embodiment, the step of constructing the water quality grade instance base comprises:
respectively acquiring historical detection data of water quality samples of a plurality of different sampling points in each water quality environment aiming at different water quality environments; and analyzing the historical detection data by using a grey correlation analysis method to obtain the water quality evaluation grade corresponding to each water quality evaluation factor in the historical detection data in each range data value, and generating a water quality grade example library, wherein the specific grey correlation analysis method can refer to the detailed description below.
S102: acquiring actual measurement data corresponding to each water quality evaluation factor of a water quality sample to be detected;
recording the content numerical value of volatile phenol of the water quality sample to be detected as xi(1) The content value of the biochemical oxygen demand is xi(2) The numerical value of the content of ammonia nitrogen is xi(3) The total phosphorus content is xi(4) The number of the sulfide is xi(5)。
S103: extracting water quality examples having the same water quality environment as the water quality samples to be detected from the water quality grade example library, and respectively carrying out similarity calculation on the actually measured data corresponding to the water quality samples and the historical detection data of each water quality example to obtain the overall similarity between the actually measured data of the water quality samples and the historical detection data of the water quality examples;
specifically, firstly, determining the water quality environment to which a water quality sample to be detected belongs, and extracting all examples in the same water quality environment from a water quality evaluation grade example library; respectively calculating the local similarity of each evaluation factor measured data of the water quality sample and each evaluation factor in each extracted example, wherein the calculation formula is as follows:
the simk (m, n) represents the local similarity of the measured data m and the instance n in the instance library on the same evaluation factor k, Δ r represents the difference between the maximum value and the minimum value of the evaluation factor k in the numerical range of each water quality level, if the current level has no upper limit or lower limit, Δ r directly takes a critical value, and Δ d is the absolute value of the difference between the measured values of the measured data m and the instance n corresponding to the evaluation factor k.
Calculating the overall similarity (simk (m, n)) between the measured data m and each instance n according to the local similarity simk (m, n) of each evaluation factor and the weight w (k) occupied by each evaluation factorallThe calculation formula is as follows:
wherein l represents the total number of the water quality evaluation factors; in this example, l ═ 5;
specifically, the user may determine the weight of each evaluation factor according to the actual situation of the local water quality environment. In this embodiment, the weight value positioning values of the five evaluation factors of volatile phenol, biochemical oxygen demand, ammonia nitrogen, total phosphorus, and sulfide are shown in the following table:
TABLE 1 evaluation factor weight values
S104: respectively comparing the overall similarity corresponding to each example with a preset value, discarding the examples with the overall similarity smaller than or equal to a preset threshold value, and selecting the examples with the maximum overall similarity from the examples as the water quality detection results of the water quality samples for the examples with the overall similarity larger than the preset threshold value;
and if the overall similarity corresponding to each example is smaller than a preset threshold value, further detecting the water quality sample by adopting a grey correlation analysis method.
Specifically, the threshold of the overall similarity is determined according to experience and actual conditions, and the present invention is not particularly limited. To further narrow the example screening range, the present embodiment sets the threshold value to 0.7.
By comparing the global similarity (simk (m, n))allAnd obtaining an example set with the overall similarity larger than 0.7 according to the threshold value, and selecting the example with the maximum similarity in the examples as the water quality evaluation result.
When the overall similarity is less than a preset threshold value of 0.7, evaluating by a grey correlation analysis method, and dividing the water quality grade into five grades of I-V by taking five evaluation factors of volatile phenol, biochemical oxygen demand, ammonia nitrogen, total phosphorus and sulfide as an example to explain the concrete steps of the grey correlation analysis method:
(1) firstly, a grey correlation analysis matrix B is constructed. Using the measured data as a reference sequence x0，x0＝{x0(k) 1,2, …, l, and taking the water quality standard grade in the example base as a comparison sequence xj,xj＝{xj(k) 1, | k ═ 1,2, …, l; j 1,2, …, i, constructing a gray correlation analysis matrix B,
wherein l represents the number of evaluation factors, j represents the grade of the water quality standard grade, in the embodiment, l takes a value of 1-5 according to the five selected evaluation factors, j takes a value of 1-5, x takes a value of 1-5 according to the five-grade water quality standard numerical value in the embodiment libraryiAnd if the standard grade of the water quality is i, corresponding historical detection data is represented, and the matrix B is as follows:
(2) next, matrix B is subjected to dimensionless processing. Because the magnitude (namely the magnitude of a measurement index) and the unit of five evaluation factors of volatile phenol, biochemical oxygen demand, ammonia nitrogen, total phosphorus and sulfide are not completely the same, different dimensions and magnitudes cannot be directly compared and evaluated in the process of multi-index comprehensive evaluation, data corresponding to each evaluation factor needs to be subjected to dimensionless treatment before the relevance degree is calculated, namely a matrix B is subjected to relevant treatment, and for a certain evaluation factor, a first-level index is defined to be normalized to 1, and a V-level index is defined to be normalized to 0. Therefore, the values of the standard normalization values of the water quality of other levels are processed by adopting piecewise linear transformation.
For the evaluation factors with larger water quality index value and deeper pollution degree, the following transformation is adopted:
for the evaluation factors with larger water quality index value and lighter pollution degree, the following transformation is adopted:
in the above formula, yi(k) Data x representing the k-th evaluation factor value in the water quality standard grade j after dimensionless5(k) Standard data, x, representing the kth evaluation factor of the fifth grade water qualityj(k) Standard data, x, representing the kth evaluation factor of the i-th water quality1(k) And standard data representing the kth evaluation factor of the first-level water quality.
The evaluation factor is subjected to the above-described dimensionless processing to obtain a processed matrix D,
wherein y isiA value y obtained by non-dimensionalizing the corresponding historical detection data when the standard grade of the water quality is i0The measured data is subjected to non-dimensionalization processing to obtain a value.
(3) Calculating the association coefficient of each evaluation factor according to the reference sequence and the comparison sequence after the non-dimensionalization treatment:
after dimensionless processing, reference sequence xiConversion to yiComparison of sequences xjConversion to yjThen, the calculation formula of the correlation coefficient is as follows:
wherein Δj＝|y0(k)-yj(k) I denotes the reference sequence y in the evaluation factor k0And comparison of the sequence yjAbsolute difference of (a)minIs the minimum value of the absolute difference, ΔmaxIs the maximum of the absolute difference, ρ is called the resolution factor, the smaller ρ is,the larger the resolution is, the more commonly ρ is 0.500;
(4) and calculating the association degree. The correlation degree is an important numerical solution in grey correlation analysis and is important for evaluating the water quality grade. In this embodiment, since there are five water quality evaluation factors, there are 5 correlation coefficients, and 5 correlation coefficients which are too scattered and have no relation are not easy to be compared in a whole, it is necessary to collect the correlation coefficients of 5 evaluation factors as a value, and to express the average of the 5 correlation coefficients as a numerical value of the degree of correlation between the comparison sequence and the reference sequence by averaging the values, and the degree of correlation ajThe formula is as follows:
(5) by degree of association ajAnd selecting the water quality grade corresponding to the comparison sequence with the maximum relevance as an evaluation result.
In one embodiment, the detection result of the water quality sample can be stored in the case base as a standard result, and the data content of the case base is enriched.
According to the technical scheme provided by the invention, the water quality grade case base is constructed, when the actually measured data of the evaluation factors are evaluated, the similarity between the data to be evaluated and the original cases in the case base is calculated by using a nearest neighbor method, when the similarity is greater than a preset threshold value, the result with the maximum similarity can be directly selected as a final evaluation result value without performing grey correlation analysis, compared with the traditional method that grey correlation analysis is performed once every time a sample is taken, the cost of water quality detection and analysis is greatly saved, and the time is shortened.
In another embodiment, the present invention provides a water quality detection system comprising:
the water quality grade real-time storage system comprises a real-time storage module, a real-time storage module and a real-time storage module, wherein the real-time storage module is used for acquiring historical water quality detection data to construct a water quality grade real-time storage, and the water quality grade real-time storage stores the historical detection data of water quality examples under different water quality environments and corresponding water quality grades; the historical detection data comprises at least one water quality evaluation factor;
the data acquisition module is used for acquiring actual measurement data corresponding to each water quality evaluation factor of the water quality sample to be detected;
the calculation module is used for extracting water quality examples with the same water quality environment as the water quality samples to be detected from the water quality grade example library, and respectively carrying out similarity calculation on the measured data corresponding to the water quality samples and the historical detection data of each water quality example to obtain the overall similarity between the measured data of the water quality samples and the historical detection data of the water quality examples;
the evaluation module is used for detecting the water quality samples by adopting a grey correlation analysis method if the overall similarity corresponding to each water quality example is smaller than a preset threshold value; otherwise, selecting the water quality grade corresponding to the water quality example with the maximum overall similarity from the water quality examples with the overall similarity larger than the preset threshold value as the detection result of the water quality sample.
In a specific embodiment, the water quality detection system further comprises a human-computer interface, namely a system interface used by a user, wherein the system interface is used for providing each evaluation factor data in the water quality input by the user, or displaying a water quality grade analysis result on the interface, and providing pollution solving measures and suggestions to enable the result to be more visual.
The working process of the embodiment of the present solution is further explained with reference to specific scenarios as follows:
in one embodiment, a user logs in the water quality detection system first, and inputs the measured content data and the weight value of each evaluation factor in the system interface, or may adopt a default weight value of the system, as shown in the following table:
| evaluation factor | Volatile phenols | Biochemical oxygen demand | Ammonia nitrogen | Total phosphorus | Sulfide compound |
| Measured data value | 0.003 | 2.97 | 1.10 | 0.19 | 0.13 |
| Weighted value | 0.250 | 0.130 | 0.390 | 0.120 | 0.110 |
The system enters an example reasoning process, overall similarity is calculated according to the actually measured data values of the evaluation factors and the weighted values in the table, an example set with the overall similarity being larger than a preset threshold value of 0.7 is deduced to exist in an example database, the example with the highest overall similarity is displayed on a system interface as a final water quality grade analysis result, and the water quality grade at this time is three-grade. As there are many villages near the monitoring point, the pollution source mainly comes from people's domestic sewage, including: a great amount of phosphate fertilizer and nitrogen fertilizer used by farmers when cultivating farmlands; various detergent effluents; domestic waste and human and poultry feces. Although the water quality at the detection point is slightly polluted, the water quality can be quoted for the daily life of people after being correspondingly treated. However, phosphorus and nitrogen elements in water sources can cause great threat to human health, and if the water sources are not treated for a long time, the pollution is more and more serious. So must follow the source and carry out the management and protection to the water quality of the sloppy river, can establish a small-size sewage treatment plant every 3 to 4 villages, with the domestic water centralized processing in several villages, break away from ammonia nitrogen, phosphorus in the sewage through means such as biology, chemistry to disinfect sewage so that people's reuse.
In another embodiment, the user inputs the measured content data and the weight values of the following evaluation factors in the system interface:
| evaluation factor | Volatile phenols | Biochemical oxygen demand | Ammonia nitrogen | Total phosphorus | Sulfide compound |
| Measured data value | 0.013 | 3.97 | 1.10 | 0.19 | 0.15 |
| Weighted value | 0.250 | 0.130 | 0.390 | 0.120 | 0.110 |
The system enters an example reasoning process, and the fact that an example set with the overall similarity larger than a preset threshold value of 0.7 does not exist in an example database is reasoned, and the grey correlation analysis process needs to be carried out. And taking the example data as a comparison sequence, taking the actual measurement data to be analyzed as a reference sequence to form a correlation matrix, carrying out non-dimensionalization processing on the data in the matrix, solving the correlation coefficient and the correlation degree of the processed data according to a formula, and finally sequencing the correlation degrees, wherein the value with the largest value is taken as the grade of the corresponding water quality grade standard as the grade of the monitoring point. The water quality of the monitoring point is deduced to be in the second grade, is suitable for domestic water and needs to be used as a key protection area.
The embodiment also provides a computer readable medium, which stores a computer program executable by an electronic device, and when the computer program runs on the electronic device, the electronic device is enabled to execute any one of the above technical solutions of the water quality assessment and inference method, which has similar implementation principles and technical effects to those of the above methods, and is not described herein again. Types of computer readable media include, but are not limited to, storage media such as SD cards, usb disks, fixed hard disks, removable hard disks, and the like.
It must be noted that in any of the above embodiments, the methods are not necessarily executed in order of sequence number, and as long as it cannot be assumed from the execution logic that they are necessarily executed in a certain order, it means that they can be executed in any other possible order.
It will be understood by those skilled in the art that the foregoing is only a preferred embodiment of the present invention, and is not intended to limit the invention, and that any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (10)
1. A water quality detection method is characterized by comprising the following steps:
obtaining historical water quality detection data to construct a water quality grade case base, wherein the historical detection data of water quality cases under different water quality environments and corresponding water quality grades are stored in the water quality grade case base; the historical detection data comprises at least one water quality evaluation factor;
acquiring actual measurement data corresponding to each water quality evaluation factor of a water quality sample to be detected;
extracting water quality examples having the same water quality environment as the water quality samples to be detected from the water quality grade example library, and respectively carrying out similarity calculation on the actually measured data corresponding to the water quality samples and the historical detection data of each water quality example to obtain the overall similarity between the actually measured data of the water quality samples and the historical detection data of the water quality examples;
if the overall similarity corresponding to each water quality example is smaller than a preset threshold value, detecting a water quality sample by adopting a grey correlation analysis method; otherwise, selecting the water quality grade corresponding to the water quality example with the maximum overall similarity from the water quality examples with the overall similarity larger than the preset threshold value as the detection result of the water quality sample.
2. The water quality detection method of claim 1, wherein the obtaining of the historical water quality detection data to construct the water quality grade instance base comprises:
acquiring historical detection data of water quality samples of a plurality of different sampling points under each water quality environment;
and analyzing the historical detection data by using a grey correlation analysis method to obtain the water quality grades corresponding to the water quality evaluation factors in the historical detection data, and generating a water quality grade example library.
3. The water quality detection method of claim 1, wherein the calculating the similarity between the measured data corresponding to the water quality sample and the historical detection data of each water quality example to obtain the overall similarity between the measured data of the water quality sample and the historical detection data of the water quality example comprises:
respectively calculating the local similarity between the actually measured data corresponding to the water quality sample and each water quality evaluation factor in the historical detection data of each water quality example;
and calculating the overall similarity between the measured data and the examples according to the local similarity of each water quality evaluation factor and the weight occupied by each water quality evaluation factor.
4. A water quality evaluation inference method according to claim 3, wherein the calculation formula of the local similarity is as follows:
overall similarity (simk (m, n))allThe calculation formula of (a) is as follows:
the simk (m, n) represents the local similarity of the actually measured data m and the instance n in the instance library on the same evaluation factor k, Δ r represents the difference between the maximum value and the minimum value of the evaluation factor k in the range degree of each grade, and Δ d is the absolute value of the difference between the k value in the actually measured data m and the k value in the instance n; l represents the number of water quality evaluation factors; (sink (m, n))allRepresenting the overall similarity of the measured data m and the example n in the example library on the l evaluation factors, and w (k) representing the weight occupied by the evaluation factor k.
5. The water quality detection method of claim 1, wherein if the overall similarity corresponding to each water quality instance is less than a preset threshold, detecting the water quality sample by using a grey correlation analysis method comprises:
taking the measured data of the water quality sample to be detected as a reference sequence, taking the water quality grade standard data as a reference sequence, constructing a grey correlation analysis matrix B,
wherein xiAnd (3) representing the corresponding historical detection data when the water quality standard grade is i, and l represents the number of evaluation factors.
6. The water quality detecting method according to claim 5, further comprising: carrying out dimensionless treatment on the actual measurement data of the water quality sample to be detected and the historical detection data of the water quality sample to obtain a matrix D,
wherein y isiA value y obtained by non-dimensionalizing the corresponding historical detection data when the standard grade of the water quality is i0The number of the evaluation factors is represented by l, which is a value obtained by subjecting measured data to non-dimensionalization processing.
7. The water quality detecting method according to claim 6, further comprising:
and calculating a correlation coefficient and a correlation degree according to the reference sequence and the comparison sequence after the non-dimensionalization processing, sequencing the correlation degrees, and taking the water quality grade corresponding to the comparison sequence with the maximum correlation degree after the sequencing as a detection result.
8. The water quality detecting method according to claim 1, wherein the water quality evaluating factors include volatile phenol, biochemical oxygen demand, ammonia nitrogen, total phosphorus, and sulfide.
9. A water quality detection system, comprising:
the water quality grade real-time storage system comprises a real-time storage module, a real-time storage module and a real-time storage module, wherein the real-time storage module is used for acquiring historical water quality detection data to construct a water quality grade real-time storage, and the water quality grade real-time storage stores the historical detection data of water quality examples under different water quality environments and corresponding water quality grades; the historical detection data comprises at least one water quality evaluation factor;
the data acquisition module is used for acquiring actual measurement data corresponding to each water quality evaluation factor of the water quality sample to be detected;
the calculation module is used for extracting water quality examples with the same water quality environment as the water quality samples to be detected from the water quality grade example library, and respectively carrying out similarity calculation on the measured data corresponding to the water quality samples and the historical detection data of each water quality example to obtain the overall similarity between the measured data of the water quality samples and the historical detection data of the water quality examples;
the evaluation module is used for detecting the water quality samples by adopting a grey correlation analysis method if the overall similarity corresponding to each water quality example is smaller than a preset threshold value; otherwise, selecting the water quality grade corresponding to the water quality example with the maximum overall similarity from the water quality examples with the overall similarity larger than the preset threshold value as the detection result of the water quality sample.
10. A computer-readable medium, in which a computer program is stored which is executable by an electronic device, and which, when run on the electronic device, causes the electronic device to perform the steps of the method of any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110998159.7A CN113702609A (en) | 2021-08-27 | 2021-08-27 | Water quality detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110998159.7A CN113702609A (en) | 2021-08-27 | 2021-08-27 | Water quality detection method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113702609A true CN113702609A (en) | 2021-11-26 |
Family
ID=78656232
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110998159.7A Pending CN113702609A (en) | 2021-08-27 | 2021-08-27 | Water quality detection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113702609A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117373556A (en) * | 2023-12-04 | 2024-01-09 | 山东清控生态环境产业发展有限公司 | Tracing instrument and system based on multidimensional data |
| CN118191257A (en) * | 2024-05-17 | 2024-06-14 | 乐百氏(广东)饮用水有限公司 | On-line monitoring method, system and storage medium for water quality of drinking water source |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104502557A (en) * | 2014-12-03 | 2015-04-08 | 航天科工仿真技术有限责任公司 | Multi-index water quality evaluation method |
| CN105913411A (en) * | 2016-05-10 | 2016-08-31 | 云南大学 | Lake water quality evaluation prediction system and method based on factor weighting model |
| CN207939741U (en) * | 2017-12-20 | 2018-10-02 | 武汉虹信技术服务有限责任公司 | The device of weak covering in a kind of intelligent recognition room |
| CN109858755A (en) * | 2018-12-28 | 2019-06-07 | 温州医科大学 | A method of evaluation Water quality |
| CN111445104A (en) * | 2020-02-27 | 2020-07-24 | 上海交通大学 | Drinking water quality evaluation method based on multi-water quality evaluation index |
| CN112580913A (en) * | 2019-09-30 | 2021-03-30 | 天津理工大学 | Rainwater reuse water quality evaluation method based on grey correlation analysis method |
| CN113269396A (en) * | 2021-04-16 | 2021-08-17 | 佛山市奥博环保技术有限公司 | Water environment risk evaluation method and system based on multilevel grey correlation |
-
2021
- 2021-08-27 CN CN202110998159.7A patent/CN113702609A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104502557A (en) * | 2014-12-03 | 2015-04-08 | 航天科工仿真技术有限责任公司 | Multi-index water quality evaluation method |
| CN105913411A (en) * | 2016-05-10 | 2016-08-31 | 云南大学 | Lake water quality evaluation prediction system and method based on factor weighting model |
| CN207939741U (en) * | 2017-12-20 | 2018-10-02 | 武汉虹信技术服务有限责任公司 | The device of weak covering in a kind of intelligent recognition room |
| CN109858755A (en) * | 2018-12-28 | 2019-06-07 | 温州医科大学 | A method of evaluation Water quality |
| CN112580913A (en) * | 2019-09-30 | 2021-03-30 | 天津理工大学 | Rainwater reuse water quality evaluation method based on grey correlation analysis method |
| CN111445104A (en) * | 2020-02-27 | 2020-07-24 | 上海交通大学 | Drinking water quality evaluation method based on multi-water quality evaluation index |
| CN113269396A (en) * | 2021-04-16 | 2021-08-17 | 佛山市奥博环保技术有限公司 | Water environment risk evaluation method and system based on multilevel grey correlation |
Non-Patent Citations (2)
| Title |
|---|
| 董婉 等: "基于灰色关联度推理的水质评价系统分析", 电子测试, no. 18, pages 40 - 43 * |
| 董婉: "基于灰色关联度推理的水质评价管理系统的研究与应用", 中国优秀硕士学位论文全文数据库 信息科技辑, no. 07 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117373556A (en) * | 2023-12-04 | 2024-01-09 | 山东清控生态环境产业发展有限公司 | Tracing instrument and system based on multidimensional data |
| CN117373556B (en) * | 2023-12-04 | 2024-02-13 | 山东清控生态环境产业发展有限公司 | Tracing instrument and system based on multidimensional data |
| CN118191257A (en) * | 2024-05-17 | 2024-06-14 | 乐百氏(广东)饮用水有限公司 | On-line monitoring method, system and storage medium for water quality of drinking water source |
| CN118191257B (en) * | 2024-05-17 | 2024-07-09 | 乐百氏(广东)饮用水有限公司 | On-line monitoring method, system and storage medium for water quality of drinking water source |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110088619A (en) | The intelligence system and method for process and assets Gernral Check-up, abnormality detection and control for waste water treatment plant or drinking water plant | |
| Amaral et al. | Activated sludge monitoring of a wastewater treatment plant using image analysis and partial least squares regression | |
| CN112001610B (en) | Agricultural non-point source pollution treatment method and device | |
| CN113702609A (en) | Water quality detection method and system | |
| CN109711674A (en) | A kind of finger-print base construction method and device traced to the source for lake and reservoir water pollution | |
| Mustapha et al. | A new quantitative overall environmental performance indicator for a wastewater treatment plant | |
| CN111080502A (en) | Big data identification method for abnormal behavior of regional enterprise data | |
| CN112288021B (en) | Medical wastewater monitoring data quality control method, device and system | |
| Molinos-Senante et al. | Benchmarking energy efficiency in drinking water treatment plants: Quantification of potential savings | |
| CN102222279A (en) | Evaluation method of leather-making industry technology based on fuzzy comprehensive evaluation method | |
| KR100965756B1 (en) | Apparatus and method for diagnosis of operating states in municipal wastewater treatment plant | |
| KR101237444B1 (en) | A system and method for diagnosis algorithm development at wastewater treatment plant operation | |
| Boyacioglu et al. | Application of factor analysis in the assessment of surface water quality in Buyuk Menderes River Basin | |
| CN111598431B (en) | Method for evaluating ecological environment bearing capacity of river basin water with function difference | |
| CN103793604A (en) | Sewage treatment soft measuring method based on RVM | |
| CN117170221A (en) | Artificial intelligence control system for sewage treatment | |
| Tian et al. | Developing a new grey dynamic modeling system for evaluation of biology and pollution indicators of the marine environment in coastal areas | |
| CN116187861A (en) | Isotope-based water quality traceability monitoring method and related device | |
| Alfaleh et al. | Is the entropy-weighted water quality index a suitable index for evaluating the groundwater quality in Ha'il, Saudi Arabia? | |
| CN117228894A (en) | Accurate aeration sewage treatment process method | |
| CN114971164A (en) | Sludge treatment equipment abnormity detection method and system based on artificial intelligence | |
| CN109273058A (en) | A kind of composite algorism for the exceeded early warning of anaerobic processes volatile fatty acid | |
| Kohen et al. | Prediction of a full scale WWTP activated sludge SVI test using an LSTM neural network | |
| Ignacio et al. | Exploring the implementation barriers of eco-toilet system in the Philippines using decision-making trial and evaluation laboratory (DEMATEL) approach | |
| CN111161802A (en) | Method for analyzing lake water pollution source by utilizing microbial biomarkers |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |