Water environment detection method based on photoelectrons

Abstract

The invention relates to the technical field of water environment detection, and discloses a photoelectron-based water environment detection method, which comprises the following steps that: a data analysis module can effectively identify an abnormal sampling point by marking and comparing the light intensity of the sampling point, and performs correction by adjusting the light intensity of a light source transmitting end, so that the detection accuracy of the abnormal sampling point is improved; measurement errors caused by uneven light sources or external interference are avoided. And secondly, the accuracy of the sampling result is further ensured by the step of verifying the secondarily collected optical signals. And finally, through comprehensive analysis of the environment score of the sampling point and the overall regional environment score, the water area environment quality can be evaluated more accurately.

Description

Technical Field

[0001] The present invention relates to the technical field of water environment detection, and in particular to a water environment detection method based on photoelectronics. Background Art

[0002] Traditional water environment detection methods usually rely on chemical analysis and physical detection methods, but these methods often have problems such as complex operation, poor real-time performance, and secondary pollution to the environment. In recent years, optoelectronic technology has gradually become an important means in the field of water environment detection due to its high sensitivity, non-contact and real-time monitoring characteristics. For example, through the absorption, scattering or reflection characteristics of light signals, the concentration of pollutants such as dissolved substances and suspended particles in water can be detected to achieve water quality assessment.

[0003] Although optoelectronic technology has shown significant advantages in water environment detection, existing detection methods still face some technical difficulties. For example, in practical applications, due to the complexity of water bodies, the optical signals at different sampling points will be affected by environmental noise and light source non-uniformity, resulting in inconsistent or even abnormal detection results at the sampling points. In addition, most current detection systems lack the function of effectively adjusting abnormal sampling points, and the reliability and accuracy of the detection results are insufficient. At the same time, the traditional water quality scoring model is also relatively rough, and it is difficult to scientifically integrate the data from the sampling points to accurately assess the regional environmental quality.

[0004] Therefore, there is an urgent need to invent a water environment detection technology to solve the problems in the existing optoelectronic water environment detection technology, such as the interference of the optical signal of the sampling point by environmental noise and light source unevenness, the lack of an effective adjustment mechanism for abnormal sampling points, and the rough water quality scoring model. Summary of the invention

[0005] In view of this, the present invention proposes a water environment detection method based on photoelectronics, which aims to solve the problems in the existing photoelectronic water environment detection technology, such as the interference of sampling point optical signals by environmental noise and light source unevenness, the lack of effective adjustment mechanism for abnormal sampling points, and the rough water quality scoring model.

[0006] The present invention proposes a water environment detection method based on photoelectrons, comprising:

[0007] The detection module uses a photoelectric sensor to sequentially obtain light signals of several sampling points in the area to be detected, the data analysis module obtains the light intensity of the light signal and obtains the average light intensity between the several sampling points, and the data analysis module marks the sampling point according to the light intensity of a single sampling point and the average light intensity;

[0008] The data analysis module determines whether the detection of the marked sampling point meets the standard according to the relationship between the light intensity of the marked sampling point and the light intensity mean;

[0009] When the data analysis module determines that the detection of the marked sampling point does not meet the standard, the light intensity of the light source transmitting end of the marked sampling point is adjusted based on the relationship between the light intensity of the marked sampling point and the light intensity mean;

[0010] After the light intensity of the light source transmitting end of the marked sampling point is adjusted, the detection module uses a photoelectric sensor to collect secondary light signals from the marked sampling point;

[0011] The data analysis module performs an environmental score on the sampling point according to the optical signal of the sampling point, and determines the environmental score of the area to be detected according to the environmental scores of several sampling points.

[0012] Furthermore, when the data analysis module marks the sampling point according to the light intensity of a single sampling point and the light intensity mean, it includes:

[0013] When the light intensity is lower than the light intensity mean, determining to mark the sampling point;

[0014] When the light intensity is consistent with the light intensity mean, it is determined that the sampling point is not marked;

[0015] When the light intensity is higher than the light intensity mean, the light intensities of two adjacent sampling points are obtained, and it is determined whether to mark the sampling point.

[0016] Further, when the light intensity is higher than the light intensity mean, the light intensity of two adjacent sampling points of the sampling point is obtained, and it is determined whether to mark the sampling point, including:

[0017] Obtaining the average light intensity between two adjacent sampling points and setting it as a first control value;

[0018] Obtaining an intensity ratio between the light intensity and the first control value, and determining whether to mark the sampling point according to the intensity ratio:

[0019] When the intensity ratio is less than or equal to 1, it is determined that the sampling point is not marked;

[0020] When the intensity ratio is greater than 1, it is determined to mark the sampling point.

[0021] Furthermore, when the data analysis module determines whether the detection of the marked sampling point meets the standard according to the relationship between the light intensity of the marked sampling point and the light intensity mean, it includes:

[0022] The data analysis module determines the deviation threshold according to the relationship between the light intensities of the sampling points:

[0023] ;

[0024] in, is the deviation threshold, a is the fluctuation coefficient, N is the total data volume of the sampling points, I i is the light intensity of the i-th sampling point;

[0025] The data analysis module determines whether the detection of the marked sampling point meets the standard according to the deviation value between the light intensity and the light intensity mean value and the relationship between the deviation value and the deviation threshold;

[0026] When the deviation value is less than or equal to the deviation threshold, it is determined that the detection of the sampling point meets the standard;

[0027] When the deviation value is greater than the deviation threshold, it is determined that the detection of the sampling point does not meet the standard.

[0028] Further, based on the relationship between the light intensity of the marked sampling point and the light intensity mean, when adjusting the light intensity of the light source transmitting end of the marked sampling point, it includes:

[0029] The data analysis module obtains the intensity difference between the light intensity of the marked sampling point and the light intensity mean, determines the adjustment coefficient according to the relationship between the intensity difference and the preset first preset intensity difference and the second preset intensity difference, and adjusts the light intensity of the light source transmitting end of the marked sampling point according to the adjustment coefficient, wherein:

[0030] When the intensity difference is less than or equal to the first preset intensity difference, determining the adjustment coefficient to be L3;

[0031] When the intensity difference is greater than the first preset intensity difference and the intensity difference is less than or equal to the second preset intensity difference, determining the adjustment coefficient to be L2;

[0032] When the intensity difference is greater than the second preset intensity difference, the adjustment coefficient is determined to be L1;

[0033] The first preset intensity difference is less than zero and less than the second preset intensity difference, and L1<L2<L3<1.

[0034] Furthermore, when the data analysis module performs environmental scoring on the sampling point according to the optical signal of the sampling point, it includes:

[0035] Acquire index data in the historical optical signals of the sampling point and two adjacent sampling points, wherein the index data includes: optical signal intensity, optical signal wavelength, optical signal frequency and optical signal phase;

[0036] Establishing a feature correlation formula according to the index data of the sampling point and two adjacent sampling points, and obtaining a distance metric between each of the feature correlation formulas;

[0037] Constructing a distance matrix according to the distance metric, and iteratively clustering the characteristic association formulas according to the distance matrix, and determining a characteristic vector of the index data between the sampling point and two adjacent sampling points based on the characteristic association formula after iterative clustering;

[0038] Obtaining index data in the optical signals of two adjacent sampling points, and substituting the index data into a feature vector of the index data to determine preset index data of the sampling points;

[0039] According to the relationship between the indicator data in the optical signal of the sampling point and the preset indicator data, the environmental scoring of the sampling point is determined.

[0040] Furthermore, when determining the environmental scoring of the sampling point according to the relationship between the indicator data in the optical signal of the sampling point and the preset indicator data, it includes:

[0041] ;

[0042] Wherein, W is the environmental score of the sampling point, M is the total number of indicator data, hi is the weight coefficient of the i-th indicator data, Si is the i-th indicator data, and si is the i-th preset indicator data.

[0043] Furthermore, when determining the characteristic vector of the index data of the sampling point and between two adjacent sampling points based on the characteristic correlation formula after iterative clustering, it includes:

[0044] Obtain the historical indicator data of any three adjacent groups of sampling points, and substitute the historical indicator data on both sides into the characteristic vector of the indicator data to obtain the preset indicator data in the middle;

[0045] According to the relationship between the historical indicator data of the sampling point and the preset indicator data, determining whether to modify the characteristic vector of the indicator data;

[0046] When the historical indicator data is consistent with the preset indicator data, it is determined that the characteristic vector of the indicator data is not to be corrected;

[0047] When the historical indicator data is inconsistent with the preset indicator data, the distance matrix is ​​corrected until the historical indicator data is consistent with the preset indicator data.

[0048] Furthermore, when determining the environmental score of the area to be detected based on the environmental scores of the plurality of sampling points, it includes:

[0049] ;

[0050] Wherein, Y is the environmental score of the area to be detected, m is the total number of the sampling points, and f k is the weight coefficient of the kth sampling point, F k Score the environment of the kth sampling point.

[0051] Compared with the prior art, the beneficial effect of the present invention is that the optical signals of several sampling points are collected in sequence by a photoelectric sensor, and the mean of the light intensity is calculated by a data analysis module, and the sampling points with abnormal light signals are marked in combination with the deviation of the light intensity of a single sampling point from the mean. This marking method based on data analysis overcomes the errors caused by noise or water body complexity in traditional detection, and improves the accuracy and reliability of the detection results of the sampling points. Secondly, for the sampling points marked as abnormal, the light intensity of the light source transmitting end of the sampling point is adjusted, and secondary collection is performed according to the change of the light signal, which effectively compensates for the influence of environmental interference on the light signal. This dynamic adjustment mechanism can not only improve the detectability of the light signal, but also optimize the data quality of the abnormal sampling point, and provide more accurate basic data for subsequent environmental scoring. Finally, the data analysis module calculates the environmental score according to the light signal of the sampling point, and generates the environmental score of the area to be detected by integrating the scoring results of several sampling points. This scoring mechanism is based on the light signal of the sampling point, combined with the statistical analysis method, so that the assessment of the regional water environment quality is more scientific and comprehensive, which helps to intuitively reflect the water quality of the area to be detected, and provides strong support for environmental management and decision-making. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0053] Figure 1 A flowchart of a photoelectron-based water environment detection method provided in an embodiment of the present invention; DETAILED DESCRIPTION

[0054] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art. It should be noted that, in the absence of conflict, the embodiments of the present invention and the features described in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0055] like Figure 1 As shown, in some embodiments of the present application, this embodiment provides a water environment detection method based on photoelectronics, including:

[0056] Step S100, the detection module uses a photoelectric sensor to sequentially obtain light signals from a number of sampling points in the area to be detected, the data analysis module obtains the light intensity of the light signal and obtains the average light intensity between the number of sampling points, and the data analysis module marks the sampling points according to the light intensity of a single sampling point and the average light intensity.

[0057] Specifically, when the data analysis module marks the sampling point according to the light intensity of a single sampling point and the light intensity mean, it includes: when the light intensity is lower than the light intensity mean, it is determined to mark the sampling point. When the light intensity is consistent with the light intensity mean, it is determined not to mark the sampling point. When the light intensity is higher than the light intensity mean, the light intensity of two adjacent sampling points of the sampling point is obtained, and it is determined whether to mark the sampling point.

[0058] Specifically, when the light intensity is higher than the light intensity mean, the light intensity of two adjacent sampling points is obtained, and it is determined whether to mark the sampling point, including: obtaining the light intensity mean between the two adjacent sampling points, and setting it as the first control value. Obtaining the intensity ratio between the light intensity and the first control value, and determining whether to mark the sampling point according to the intensity ratio: when the intensity ratio is less than or equal to 1, it is determined not to mark the sampling point. When the intensity ratio is greater than 1, it is determined to mark the sampling point.

[0059] It can be seen that the data analysis module obtains the light intensity of the sampling point and compares it with the mean light intensity of several sampling points to determine whether the sampling point needs to be marked. When the light intensity is lower than the mean light intensity, it means that the light signal of the sampling point may be abnormally weak, and the system directly marks the sampling point; when the light intensity is consistent with the mean light intensity, it means that the light signal of the sampling point is in the normal distribution range and does not need to be marked. This preliminary marking method uses the mean light intensity as a benchmark to quickly screen out sampling points that may have problems, providing a basis for subsequent precise analysis. Secondly, for sampling points whose light intensity is higher than the mean light intensity, the light intensity of the two adjacent sampling points of the sampling point is further obtained, and the mean light intensity of the two adjacent points is calculated (i.e., the first control value). By comparing the light intensity of the current sampling point with the first control value, the abnormality of the light signal of the sampling point can be further analyzed. This method effectively avoids the misjudgment of the high light intensity of a single point due to random environmental noise or local light source interference by introducing adjacent point data, and improves the scientificity and accuracy of the judgment. Finally, in the in-depth judgment stage, by calculating the intensity ratio between the light intensity of the sampling point and the first control value, quantitative analysis is performed to determine whether the light signal of the sampling point significantly deviates from the distribution trend of the adjacent points. When the intensity ratio is less than or equal to 1, it indicates that the light intensity of the sampling point is consistent with the light signal distribution of the adjacent points, and no marking is required; when the intensity ratio is greater than 1, it indicates that the light intensity of the sampling point is significantly higher, and there is a significant difference in the signal trend of the adjacent points, and it needs to be marked. The introduction of this intensity ratio makes the marking judgment more accurate, can effectively identify abnormal sampling points, and ensure the reliability of data analysis.

[0060] Step S200: The data analysis module determines whether the detection of the marked sampling point meets the standard according to the relationship between the light intensity of the marked sampling point and the light intensity mean.

[0061] Specifically, when the data analysis module determines whether the detection of the marked sampling point meets the standard according to the relationship between the light intensity of the marked sampling point and the light intensity mean, the data analysis module determines the deviation threshold according to the relationship between the light intensities of several sampling points:

[0062] .

[0063] in, is the deviation threshold, a is the fluctuation coefficient, N is the total data volume of several sampling points, I i is the light intensity of the i-th sampling point. The data analysis module determines whether the detection of the marked sampling point meets the standard according to the deviation value between the light intensity and the mean light intensity, and according to the relationship between the deviation value and the deviation threshold: when the deviation value is less than or equal to the deviation threshold, it is determined that the detection of the sampling point meets the standard. When the deviation value is greater than the deviation threshold, it is determined that the detection of the sampling point does not meet the standard.

[0064] It can be seen that the data analysis module first calculates the deviation threshold according to the relationship between the light intensity of several sampling points. The calculation formula of the deviation threshold includes the fluctuation coefficient a, the total data volume N of the sampling points, and the light intensity Ii of each sampling point. This method obtains a global deviation threshold by comprehensively considering the light intensity fluctuation of all sampling points. The fluctuation coefficient a reflects the fluctuation characteristics of the data set, while N and Ii ensure that the calculation of the deviation threshold can reflect the variation range of the overall data distribution. Through this threshold, the deviation of the sampling point can be quantitatively evaluated to provide a basis for subsequent standard determination. Secondly, the data analysis module calculates the deviation value between the light intensity of each sampling point and the light intensity mean, and further compares the deviation value with the calculated deviation threshold. When the deviation value is less than or equal to the deviation threshold, it means that the light intensity change of the sampling point is within the allowable range and the detection result meets the standard; when the deviation value is greater than the deviation threshold, it means that the light intensity of the sampling point is abnormal and exceeds the allowable variation range, and the detection result does not meet the standard. This process can determine whether the light intensity of the sampling point meets the predetermined standard by comparing the deviation value with the deviation threshold. Finally, based on the relationship between the above deviation value and the deviation threshold, the data analysis module can determine whether the detection result of each sampling point meets the standard. When the deviation value is less than or equal to the deviation threshold, it indicates that the light intensity fluctuation of the sampling point is within the normal range and will not affect the accuracy of the detection. Therefore, the sampling point is judged to meet the standard; conversely, when the deviation value exceeds the deviation threshold, it indicates that the light signal of the sampling point deviates from the standard range and needs to be adjusted or marked as non-compliant. This judgment process makes the judgment of whether the light signal of the sampling point meets the standard more accurate and scientific through quantitative deviation calculation and comparison.

[0065] Step S300: When the data analysis module determines that the detection of the marked sampling point does not meet the standard, the light intensity of the light source transmitting end of the marked sampling point is adjusted based on the relationship between the light intensity of the marked sampling point and the light intensity mean.

[0066] Specifically, based on the relationship between the light intensity of the marked sampling point and the light intensity mean, when the light intensity of the light source transmitting end of the marked sampling point is adjusted, it includes: the data analysis module obtains the intensity difference between the light intensity of the marked sampling point and the light intensity mean, determines the adjustment coefficient according to the relationship between the intensity difference and the first preset intensity difference and the second preset intensity difference, and adjusts the light intensity of the light source transmitting end of the marked sampling point according to the adjustment coefficient, wherein: when the intensity difference is less than or equal to the first preset intensity difference, the adjustment coefficient is determined to be L3. When the intensity difference is greater than the first preset intensity difference, and the intensity difference is less than or equal to the second preset intensity difference, the adjustment coefficient is determined to be L2. When the intensity difference is greater than the second preset intensity difference, the adjustment coefficient is determined to be L1. Among them, the first preset intensity difference is less than zero and less than the second preset intensity difference, and L1<L2<L3<1.

[0067] It can be seen that the data analysis module first calculates the intensity difference between the light intensity of the marked sampling point and the mean light intensity, and compares the difference with two preset intensity differences (the first preset intensity difference and the second preset intensity difference). This process provides a basis for subsequent adjustments by quantifying the deviation between the light intensity of the sampling point and the mean. By setting the upper and lower limits of the intensity difference, the degree of deviation can be accurately judged according to the relationship between the light intensity of the sampling point and the mean, and different adjustment strategies can be adopted accordingly. Secondly, according to the relationship between the intensity difference and the preset intensity difference, the data analysis module will determine an adjustment coefficient, which is used to adjust the light intensity of the light source at the transmitting end. This adjustment mechanism makes the adjustment of light intensity more accurate and meets the requirements of different degrees of deviation through hierarchical coefficient changes. Finally, by using the adjustment coefficients L1, L2, and L3 to adjust the light intensity at the transmitting end of the light source, the system can accurately correct the light intensity of the marked sampling point to make it close to the mean light intensity. This step-by-step adjustment method ensures that the recovery of light intensity is neither excessive nor insufficient, avoiding the problem of over-adjustment or under-adjustment.

[0068] Step S400: After the light intensity of the light source transmitting end of the marked sampling point is adjusted, the detection module uses a photoelectric sensor to collect secondary light signals from the marked sampling point.

[0069] Step S500: The data analysis module performs an environmental score on the sampling point according to the optical signal of the sampling point, and determines the environmental score of the area to be detected according to the environmental scores of several sampling points.

[0070] Specifically, when the data analysis module performs an environmental scoring on the sampling point according to the optical signal of the sampling point, it includes: obtaining the index data in the historical optical signals of the sampling point and the two adjacent sampling points, wherein the index data includes: optical signal intensity, optical signal wavelength, optical signal frequency and optical signal phase. Establish a feature correlation formula based on the index data of the sampling point and the two adjacent sampling points, and obtain the distance metric between each feature correlation formula. Construct a distance matrix based on the distance metric, and iteratively cluster each feature correlation formula based on the distance matrix, and determine the feature vector of the index data between the sampling point and the two adjacent sampling points based on the feature correlation formula after iterative clustering. Obtain the index data in the optical signals of the two adjacent sampling points, and substitute it into the feature vector of the index data to determine the preset index data of the sampling point. According to the relationship between the index data in the optical signal of the sampling point and the preset index data, determine the environmental scoring of the sampling point.

[0071] Specifically, when determining the characteristic vector of the indicator data between the sampling point and two adjacent sampling points based on the characteristic correlation formula after iterative clustering, it includes: obtaining the historical indicator data of any three adjacent groups of sampling points, and substituting the historical indicator data on both sides into the characteristic vector of the indicator data to obtain the intermediate preset indicator data. According to the relationship between the historical indicator data of the intermediate sampling point and the preset indicator data, it is determined that the characteristic vector of the indicator data is corrected. When the historical indicator data is consistent with the preset indicator data, it is determined that the characteristic vector of the indicator data is not corrected. When the historical indicator data is inconsistent with the preset indicator data, the distance matrix is ​​corrected until the historical indicator data is consistent with the preset indicator data.

[0072] Specifically, according to the relationship between the indicator data in the optical signal of the sampling point and the preset indicator data, when determining the environmental scoring of the sampling point, it includes:

[0073] .

[0074] Among them, W is the environmental score of the sampling point, M is the total number of indicator data, hi is the weight coefficient of the i-th indicator data, Si is the i-th indicator data, and si is the i-th preset indicator data.

[0075] It can be seen that the data analysis module first obtains the various indicator data (such as optical signal intensity, wavelength, frequency, phase, etc.) in the historical optical signals of the sampling point and its two adjacent sampling points, and uses these data to establish a characteristic correlation formula. The characteristic correlation formula is used to describe the intrinsic relationship between these indicator data, and then construct a distance matrix through distance measurement. The role of the distance matrix is ​​to quantify the difference in indicator data between each sampling point and its adjacent points, ensuring that the subsequent clustering and scoring process can fully consider the similarities and differences between the data. This construction method further refines the data grouping through iterative clustering, and finally extracts the feature vector of each sampling point, providing a basis for environmental scoring. Secondly, based on the characteristic correlation formula after iterative clustering, the data analysis module will continue to adjust the feature vector of the sampling point and its two adjacent sampling points. In this process, the relationship between the historical indicator data and the preset indicator data is used to correct the feature vector. When the historical indicator data is consistent with the preset indicator data, the feature vector does not need to be corrected; when they are inconsistent, the feature vector will be adjusted by correcting the distance matrix until the data is consistent. This correction process continuously updates the feature vector to ensure that the final feature data is more accurate, thereby improving the accuracy of the environmental score. Finally, after determining the relationship between the optical signal at the sampling point and the preset indicator data, the data analysis module will calculate the environmental score based on the difference between each indicator data and its preset value. Specifically, the environmental score (W) of the sampling point is obtained by weighted summing up various indicator data (such as light intensity, frequency, etc.), where each indicator data (Si) has a weight coefficient (hi), which reflects the importance of the indicator to the environmental score. By comprehensively considering the weights of all indicator data and the relationship between actual data and preset data, a comprehensive and accurate environmental score can be obtained, thereby accurately reflecting the environmental quality of the area to be tested.

[0076] Specifically, the environmental scores of the area to be tested are determined based on the environmental scores of several sampling points, including:

[0077] .

[0078] Among them, Y is the environmental score of the area to be detected, m is the total number of sampling points, and f k is the weight coefficient of the kth sampling point, F k Score the environment of the kth sampling point.

[0079] In the above embodiments, the optical signals of a number of sampling points are sequentially collected by a photoelectric sensor, and the data analysis module is used to calculate the mean value of the light intensity. By combining the deviation between the light intensity of a single sampling point and the mean value for marking, sampling points with abnormal optical signals can be accurately identified. This marking method based on data analysis overcomes the errors caused by noise or water body complexity in traditional detection, improving the accuracy and reliability of the detection results for sampling points. Secondly, for the sampling points marked as abnormal, the light intensity of the light source emission end of the sampling point is adjusted, and secondary collection is performed according to the change of the optical signal, effectively compensating for the influence of environmental interference on the optical signal. This dynamic adjustment mechanism can not only improve the detectability of the optical signal, but also optimize the data quality of abnormal sampling points, providing more accurate basic data for subsequent environmental scoring. Finally, the data analysis module calculates the environmental score based on the optical signal of the sampling point, and generates the environmental score of the area to be detected by integrating the scoring results of a number of sampling points. This scoring mechanism is based on the optical signal of the sampling point and combines statistical analysis methods, making the evaluation of the regional water environment quality more scientific and comprehensive, helping to intuitively reflect the water quality status of the area to be detected, and providing strong support for environmental management and decision-making.

[0080] Those skilled in the art should understand that the embodiments of the present application can be provided as a method, a system, or a computer program product. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0081] The present application is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of the present application. It should be understood that each flow and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of flows and / or blocks in the flowchart and / or block diagram can also be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for realizing the functions specified in Figure 1 one or more of the flows or multiple flows and / or blocks Figure 1 one or more of the blocks or multiple blocks.

[0082] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device, and the instruction device realizes the functions in the process Figure 1A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0083] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0084] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions 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. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A water environment detection method based on photoelectrons, characterized in that: include: The detection module uses a photoelectric sensor to sequentially obtain light signals of several sampling points in the area to be detected, the data analysis module obtains the light intensity of the light signal and obtains the average light intensity between the several sampling points, and the data analysis module marks the sampling point according to the light intensity of a single sampling point and the average light intensity; The data analysis module determines whether the detection of the marked sampling point meets the standard according to the relationship between the light intensity of the marked sampling point and the light intensity mean; When the data analysis module determines that the detection of the marked sampling point does not meet the standard, the light intensity of the light source transmitting end of the marked sampling point is adjusted based on the relationship between the light intensity of the marked sampling point and the light intensity mean; After the light intensity of the light source transmitting end of the marked sampling point is adjusted, the detection module uses a photoelectric sensor to collect secondary light signals from the marked sampling point; The data analysis module performs an environmental score on the sampling point according to the optical signal of the sampling point, and determines the environmental score of the area to be detected according to the environmental scores of several sampling points.

2. The photoelectron-based water environment detection method according to claim 1, characterized in that: When the data analysis module marks the sampling point according to the light intensity of a single sampling point and the light intensity mean, it includes: When the light intensity is lower than the light intensity mean, determining to mark the sampling point; When the light intensity is consistent with the light intensity mean, it is determined that the sampling point is not marked; When the light intensity is higher than the light intensity mean, the light intensities of two adjacent sampling points are obtained, and it is determined whether to mark the sampling point.

3. The photoelectron-based water environment detection method according to claim 2, characterized in that: When the light intensity is higher than the light intensity mean, obtaining the light intensity of two adjacent sampling points of the sampling point and determining whether to mark the sampling point includes: Obtaining the average light intensity between two adjacent sampling points and setting it as a first control value; Obtaining an intensity ratio between the light intensity and the first control value, and determining whether to mark the sampling point according to the intensity ratio: When the intensity ratio is less than or equal to 1, it is determined that the sampling point is not marked; When the intensity ratio is greater than 1, it is determined to mark the sampling point.

4. The photoelectron-based water environment detection method according to claim 1, characterized in that: When the data analysis module determines whether the detection of the marked sampling point meets the standard according to the relationship between the light intensity of the marked sampling point and the light intensity mean, it includes: The data analysis module determines the deviation threshold according to the relationship between the light intensities of the sampling points: ; in, is the deviation threshold, a is the fluctuation coefficient, N is the total data volume of the sampling points, I i is the light intensity of the i-th sampling point; The data analysis module determines whether the detection of the marked sampling point meets the standard according to the deviation value between the light intensity and the light intensity mean value and the relationship between the deviation value and the deviation threshold; When the deviation value is less than or equal to the deviation threshold, it is determined that the detection of the sampling point meets the standard; When the deviation value is greater than the deviation threshold, it is determined that the detection of the sampling point does not meet the standard.

5. The photoelectron-based water environment detection method according to claim 1, characterized in that: When adjusting the light intensity of the light source transmitting end of the marked sampling point based on the relationship between the light intensity of the marked sampling point and the light intensity mean, the method includes: The data analysis module obtains the intensity difference between the light intensity of the marked sampling point and the light intensity mean, determines the adjustment coefficient according to the relationship between the intensity difference and the preset first preset intensity difference and the second preset intensity difference, and adjusts the light intensity of the light source transmitting end of the marked sampling point according to the adjustment coefficient, wherein: When the intensity difference is less than or equal to the first preset intensity difference, determining the adjustment coefficient to be L3; When the intensity difference is greater than the first preset intensity difference and the intensity difference is less than or equal to the second preset intensity difference, determining the adjustment coefficient to be L2; When the intensity difference is greater than the second preset intensity difference, the adjustment coefficient is determined to be L1; The first preset intensity difference is less than zero and less than the second preset intensity difference, and L1<L2<L3<1.

6. The photoelectron-based water environment detection method according to claim 1, characterized in that: When the data analysis module performs environmental scoring on the sampling point according to the optical signal of the sampling point, it includes: Acquire index data in the historical optical signals of the sampling point and two adjacent sampling points, wherein the index data includes: optical signal intensity, optical signal wavelength, optical signal frequency and optical signal phase; Establishing a feature correlation formula according to the index data of the sampling point and two adjacent sampling points, and obtaining a distance metric between each of the feature correlation formulas; Constructing a distance matrix according to the distance metric, and iteratively clustering the characteristic association formulas according to the distance matrix, and determining a characteristic vector of the index data between the sampling point and two adjacent sampling points based on the characteristic association formula after iterative clustering; Obtaining index data in the optical signals of two adjacent sampling points, and substituting the index data into a feature vector of the index data to determine preset index data of the sampling points; According to the relationship between the indicator data in the optical signal of the sampling point and the preset indicator data, the environmental scoring of the sampling point is determined.

7. The photoelectron-based water environment detection method according to claim 6, characterized in that: When determining the environmental scoring of the sampling point according to the relationship between the indicator data in the optical signal of the sampling point and the preset indicator data, the method includes: ; Wherein, W is the environmental score of the sampling point, M is the total number of indicator data, hi is the weight coefficient of the i-th indicator data, Si is the i-th indicator data, and si is the i-th preset indicator data.

8. The photoelectron-based water environment detection method according to claim 6, characterized in that: When determining the characteristic vector of the index data of the sampling point and two adjacent sampling points based on the characteristic correlation formula after iterative clustering, it includes: Obtain the historical indicator data of any three adjacent groups of sampling points, and substitute the historical indicator data on both sides into the characteristic vector of the indicator data to obtain the preset indicator data in the middle; According to the relationship between the historical indicator data of the sampling point and the preset indicator data, determining whether to modify the characteristic vector of the indicator data; When the historical indicator data is consistent with the preset indicator data, it is determined that the characteristic vector of the indicator data is not to be corrected; When the historical indicator data is inconsistent with the preset indicator data, the distance matrix is ​​corrected until the historical indicator data is consistent with the preset indicator data.

9. The photoelectron-based water environment detection method according to claim 1, characterized in that: When determining the environmental score of the area to be tested based on the environmental scores of the sampling points, it includes: ; Wherein, Y is the environmental score of the area to be detected, m is the total number of the sampling points, and f k is the weight coefficient of the kth sampling point, F k Score the environment of the kth sampling point.

Images