Online sewage toxicity early warning method based on intelligent sensor

Abstract

The invention discloses an on-line sewage toxicity early warning method based on an intelligent sensor, and relates to the technical field of intelligent sensors, and the method specifically comprises the steps: collecting introduction difference information of sewage original data collected by each intelligent sensor and transmission fluctuation information of the sewage original data transmitted by each intelligent sensor, and obtaining an introduction difference coefficient and a transmission fluctuation coefficient; the method comprises the steps of constructing an abnormal fluctuation model, generating an abnormal fluctuation coefficient, constructing a fusion efficiency model to evaluate the fusion effect of original sewage data, generating a fusion efficiency index, and carrying out risk verification on sewage toxicity output according to the abnormal fluctuation index and the fusion efficiency index. The problem that it is difficult for managers to determine the exact fault link of the input error due to the sewage toxicity early warning fault is avoided, the verification efficiency of the original sewage data is improved, the data reaction timeliness of online sewage toxicity early warning is improved, and the fault removal process of the input error is shortened.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent sensors, and more specifically, to an online sewage toxicity early warning method based on intelligent sensors. Background Art

[0002] Online sewage toxicity warning based on smart sensors uses smart sensor technology to monitor the concentration of harmful substances, toxicity levels and environmental changes in sewage in real time, and to warn of potential pollution accidents or ecological hazards in advance. The smart sensor parameters monitored by the online sewage toxicity warning cover a wide range, including chemical composition, pH value, dissolved oxygen, conductivity, temperature and other data in sewage. The detection principles of various smart sensors are different. The time spent by smart sensors from introducing sewage samples to obtaining sewage raw data varies, and the frequency of transmitting sewage raw data by each smart sensor is also different. The difference in the time spent from introducing sewage samples to obtaining sewage raw data is superimposed on the difference in the frequency of transmitting sewage raw data, which not only increases the difficulty of data synchronization, but also creates a burden on the fusion processing of various sewage raw data. Unstable differential fluctuations will also cause errors in the online sewage toxicity warning, making it difficult for managers who monitor sewage toxicity changes to confirm whether the abnormal fluctuations in sewage toxicity are caused by the collection and transmission process of sewage raw data.

[0003] In order to solve the above defects, a technical solution is now proposed. Summary of the invention

[0004] The purpose of the present invention is to provide an online sewage toxicity early warning method based on an intelligent sensor to solve the deficiencies in the background technology.

[0005] In order to achieve the above object, the present invention provides the following technical solution: an online sewage toxicity early warning method based on an intelligent sensor, the specific steps comprising:

[0006] Collect the introduced difference information of the original sewage data collected by each intelligent sensor and the transmission volatility information of the original sewage data, and obtain the introduced difference coefficient according to the introduced difference information, and obtain the transmission volatility coefficient according to the transmission volatility information;

[0007] An abnormal fluctuation model is constructed by introducing the difference coefficient and the transmission fluctuation coefficient to evaluate the stability of the operating status of each intelligent sensor for sewage toxicity monitoring and generate an abnormal fluctuation coefficient;

[0008] Data fusion is performed based on the original sewage data collected by each intelligent sensor, a fusion efficiency model is constructed to evaluate the fusion effect of the original sewage data, and a fusion efficiency index is generated;

[0009] Risk verification of sewage toxicity output is carried out based on abnormal fluctuation index and fusion efficiency index.

[0010] Preferably, the method for obtaining the introduced difference information is:

[0011] Obtain the time consumption of the original sewage data collected by each smart sensor within the time period T, record the timestamp Ts1 of the sewage sample introduced into each smart sensor and the timestamp Ts2 of each smart sensor obtaining the original sewage data, and calculate the time consumption of the original sewage data collection as Ts c =Ts2-Ts1, where Ts c is the time consumption of collecting the original data of sewage, c is the serial number of each intelligent sensor, and c={1,2,3…v}, where v is a positive integer;

[0012] Set the introduced deposition threshold to Id th , mark the time taken to collect the original sewage data as greater than or equal to the introduced sedimentation threshold Id th The data is the over-limit value Ex l , where l is the excess value Ex l , and l={1,2,3…k}, where k is a positive integer;

[0013] The introduced difference information within the calculation time period T is Among them, Ex ag Ex l The average value of

[0014] Preferably, the method for obtaining the introduced difference coefficient according to the introduced difference information is:

[0015] The intelligent sensor whose original sewage data collection time exceeds the limit value within the calibration time period T is 0, and the intelligent sensor whose original sewage data collection time does not exceed the limit value within the calibration time period T is 1. The introduction sequence is generated according to the timestamp order of the sewage samples introduced by each intelligent sensor, and the introduction sequence consists of 0 and 1;

[0016] The number of 0 introduced into the sequence is 0 t , the number of 1s introduced into the sequence is No t , the number of consecutive 0s between two adjacent 1s is Con t , then the calculation expression of the difference coefficient is introduced as

[0017] Preferably, the method for collecting the transmission volatility information of the original sewage data transmitted by each intelligent sensor and obtaining the transmission volatility coefficient according to the transmission volatility information is:

[0018] The optimal range of continuous transmission is set for the transmission rate of each intelligent sensor to transmit the original sewage data, and the optimal range of continuous transmission of each intelligent sensor to transmit the original sewage data is marked as [Orf min,Orf max ], among which Orf min is the minimum value of the optimal range of coherent transmission, Orf max is the maximum value of the optimal range for coherent transmission;

[0019] Obtain the transmission rate data of the original sewage data transmitted by each intelligent sensor within the time period T, and mark the transmission rate data of the original sewage data transmitted by each intelligent sensor within the time period T as Co t , where t is the number of the transmission rate data, and t={1,2,3…y}, where y is a positive integer;

[0020] The transmission rate data of the original sewage data transmitted by each intelligent sensor within the time period T does not belong to the optimal range of continuous transmission [Orf min ,Orf max ] and marks it as not within the optimal range for continuous transmission [Org min ,Orf max ] is the transmission rate data of the transmission volatility information Uo r , where r is not in the optimal range of coherent transmission [Orf min ,Orf max ], and r = {1, 2, 3 ... e}, where e is a positive integer;

[0021] According to the transmission volatility information Uo r Get the transmission fluctuation coefficient. The calculation expression of the transmission fluctuation coefficient is:

[0022] Preferably, the logic for constructing an abnormal fluctuation model and generating an abnormal fluctuation coefficient is:

[0023] After normalizing the introduced difference coefficient and the transmission fluctuation coefficient, the abnormal fluctuation model is constructed. The expression of the abnormal fluctuation model is: In the formula, Ab fl is the abnormal fluctuation coefficient, α and β are the weight coefficients of the introduced difference coefficient and the transmission fluctuation coefficient, respectively, and both α and β are positive numbers.

[0024] Preferably, the method for data fusion based on the original sewage data collected by each intelligent sensor is:

[0025] The weighted average method is used to obtain the original sewage data after fusion. The calculation expression of the weighted average method is: Among them, Cf c is the original sewage data after fusion, w c is the weight coefficient based on the signal-to-noise ratio, Co cis the output value of the cth smart sensor, c is the number of the smart sensor, and c={1,2,3…v}, where v is a positive integer.

[0026] Preferably, the method of constructing a fusion efficiency model and generating a fusion efficiency index is:

[0027] The signal-to-noise ratio of each sewage raw data before fusion is calibrated as Snr b , where b is the serial number of each sewage original data, and b = {1, 2, 3…x}, where x is a positive integer, and the signal-to-noise ratio of each sewage original data after fusion is Snf b ;

[0028] The standard deviation of the original sewage data after fusion is calculated as In the formula, C va is the average value of the fused sewage data, and the calculation expression is:

[0029] Then the expression of the fusion efficiency model is In the formula, F ei is the fusion efficiency index.

[0030] Preferably, the logic of risk verification is:

[0031] Set the abnormal fluctuation threshold Af for the abnormal fluctuation index th , set the fusion efficiency threshold Fe for the fusion efficiency index th , when the abnormal volatility index Ab fl Greater than or equal to the abnormal fluctuation threshold Af th , and the fusion efficiency index F ei Less than or equal to the fusion efficiency threshold Fe th When the signal fluctuation of the mark detection is abnormal and the data fusion is inaccurate, the management personnel are prompted to maintain each intelligent sensor and inspect the transmission line;

[0032] When the abnormal volatility index Ab fl Greater than or equal to the abnormal fluctuation threshold Af th , and the fusion efficiency index F ei Greater than the fusion efficiency threshold Fe th When the signal fluctuation is abnormal, the mark detection signal will be marked to remind the management personnel to maintain each smart sensor;

[0033] When the abnormal volatility index Ab fl Less than the abnormal fluctuation threshold Af th , and the fusion efficiency index F ei Less than or equal to the fusion efficiency threshold Fe th When the data fusion is inaccurate, the management personnel are prompted to inspect the transmission line;

[0034] When the abnormal volatility index Ab fl Less than the abnormal fluctuation threshold Af th , and the fusion efficiency index F ei Greater than the fusion efficiency threshold Fe th When doing so, the original sewage data shall be recorded and saved without prompting the management personnel.

[0035] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0036] This application evaluates the differences in the time consumption of each intelligent sensor for detecting sewage samples, as well as the differences in delays in the transmission process of the sewage raw data. Before data fusion processing, the delay status of the sewage raw data is comprehensively evaluated. After data fusion processing, the efficiency of data fusion is tested. Combined with data collection and data fusion, the validity of the original sewage data is comprehensively verified, which effectively improves the accuracy of sewage toxicity warning, avoids the problem that the failure of sewage toxicity warning makes it difficult for managers to determine the exact fault link of the input error, improves the verification efficiency of the sewage raw data, improves the data response timeliness of online sewage toxicity warning, and shortens the troubleshooting process of input errors. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0038] Figure 1 The figure is a flow chart of the method of the present invention. DETAILED DESCRIPTION

[0039] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0040] Example 1: Please refer to Figure 1 As shown, the present invention is an online sewage toxicity early warning method based on intelligent sensors, and the specific steps include:

[0041] Collect the introduced difference information of the original sewage data collected by each intelligent sensor and the transmission volatility information of the original sewage data, and obtain the introduced difference coefficient according to the introduced difference information, and obtain the transmission volatility coefficient according to the transmission volatility information;

[0042] An abnormal fluctuation model is constructed by introducing the difference coefficient and the transmission fluctuation coefficient to evaluate the stability of the operating status of each intelligent sensor for sewage toxicity monitoring and generate an abnormal fluctuation coefficient;

[0043] Data fusion is performed based on the original sewage data collected by each intelligent sensor, a fusion efficiency model is constructed to evaluate the fusion effect of the original sewage data, and a fusion efficiency index is generated;

[0044] Risk verification of sewage toxicity output is carried out based on abnormal fluctuation index and fusion efficiency index.

[0045] Taking the monitoring of heavy metal ions in sewage as an example, heavy metal ions in sewage, including lead, mercury, cadmium, etc., are detected by intelligent sensors. Commonly used sensors include electrochemical sensors, optical sensors, etc. Electrochemical sensors use anodic stripping voltammetry to measure electrochemical signals to detect heavy metal concentrations. Electrochemical signals include potential, current, conductivity, etc. Optical sensors detect heavy metal concentrations based on changes in fluorescence, absorption and light reflection characteristics. After the sewage is introduced into the sensor, suspended matter and particulate impurities are removed by filtration to allow heavy metal ions to contact the sensor detection area. The selectivity of heavy metal ions to the sensor is improved by adjusting the pH value of the sewage or adding chelating agents or buffer solutions. The electrode surface of the electrochemical sensor undergoes reduction or oxidation reactions with heavy metal ions, and converts the reduction or oxidation reactions into electrical signals to obtain the original sewage data. Optical sensors react heavy metal ions with fluorescent molecules or The color reagent reacts, causing the optical sensor's electrical signal to change and obtain the original sewage data. In different links of sewage monitoring, different smart sensors have different acquisition times for the original sewage data. For example, electrochemical sensors require a certain amount of electrochemical deposition time, which is measured in minutes, while optical sensors have high detection efficiency and obtain the original sewage data in seconds. Different smart sensors use different detection principles, and the time taken from introducing sewage samples to obtaining the original sewage data is different. Different harmful substances in sewage have different detection methods. In the detection process of smart sensors, there may be links to adjust the pH value or add auxiliary reagents. For sewage samples with suspended particles, filtering treatment is required before detection, which affects the detection time of smart sensors. That is, different smart sensors have differences in the time taken to obtain the original sewage data by introducing sewage samples;

[0046] If the difference in the time taken by different smart sensors to obtain the original sewage data is not resolved, the following adverse consequences will occur:

[0047] The data from different sensors correspond to different time points, and it is impossible to obtain the actual state of the sewage at the same time. As a result, when the original sewage data is fused, the mixed time information will lead to inaccurate concentration assessment of harmful substances in sewage, and thus misjudge the concentration change trend of harmful substances in sewage;

[0048] Data time asynchrony causes abnormal concentrations of some pollutants to be delayed or completely missed, resulting in delayed warning time and missed sewage toxicity management windows. At the same time, data misreporting triggers unnecessary management measures, increasing operating costs;

[0049] When the sensor times are not synchronized, it is difficult to identify the noise or erroneous data hidden in the timing differences, and it is impossible to find and eliminate faulty sensors or data anomalies in time. Abnormal data can mislead sewage toxicity assessment and lead to wrong decisions.

[0050] The accuracy and timeliness of data processing in sewage treatment links that rely on sewage toxicity warnings are affected, and sewage treatment cannot be effectively adjusted synchronously to perform real-time control of dosage and flow;

[0051] The unsynchronized sewage raw data introduces random errors into the online sewage toxicity assessment model, making it difficult for the online sewage toxicity assessment model to grasp the changing pattern of pollutant concentrations, and reducing the accuracy and system robustness of the online sewage toxicity assessment model.

[0052] The variable relationship of multiple smart sensors working together is distorted due to data asynchrony, resulting in misjudgment of the causal relationship between pollutant concentrations and environmental factors, and inability to predict future trends in pollutant diffusion or changes in sewage toxicity.

[0053] In order to avoid the above adverse effects, the difference information of the original sewage data collected by each intelligent sensor and the transmission volatility information of the original sewage data are collected. The method for obtaining the difference information is as follows:

[0054] Obtain the time consumption of the original sewage data collected by each smart sensor within the time period T, record the timestamp Ts1 of the sewage sample introduced into each smart sensor and the timestamp Ts2 of each smart sensor obtaining the original sewage data, and calculate the time consumption of the original sewage data collection as Ts c =Ts2-Ts1, where Ts c is the time consumption of collecting the original data of sewage, c is the serial number of each intelligent sensor, and c={1,2,3…v}, where v is a positive integer;

[0055] Set the introduced deposition threshold to Id th , mark the time taken to collect the original sewage data as greater than or equal to the introduced sedimentation threshold Id th The data is the over-limit value Ex l , where l is the excess value Ex l , and l={1,2,3…k}, where k is a positive integer;

[0056] The introduced difference information within the calculation time period T is Among them, Exag Ex l The average value of

[0057] It should be noted that the introduction of the sedimentation threshold is set according to the detection time consumed by the smart sensor to detect sewage samples. Under the premise of ensuring the monitoring accuracy of the smart sensor, the detection time of the smart sensor for the introduced pollutant samples is limited. The specific value of the introduction of the sedimentation threshold is set by professional and technical personnel in this field according to the principles and performance of the sensor used.

[0058] The method for obtaining the introduced difference coefficient according to the introduced difference information is:

[0059] The intelligent sensor whose original sewage data collection time exceeds the limit value within the calibration time period T is 0, and the intelligent sensor whose original sewage data collection time does not exceed the limit value within the calibration time period T is 1. The introduction sequence is generated according to the timestamp order of the sewage samples introduced by each intelligent sensor, and the introduction sequence consists of 0 and 1;

[0060] The number of 0 introduced into the sequence is 0 t , the number of 1s introduced into the sequence is No t , the number of consecutive 0s between two adjacent 1s is Con t , then the calculation expression of the difference coefficient is introduced as

[0061] Different smart sensors have different transmission and processing efficiencies for the original sewage data after acquiring it. The complexity of the signal processing algorithms used by smart sensors is different, and the data transmission speed and signal bandwidth are different. Therefore, the efficiency of transmitting the original sewage data by each smart sensor is different. If the transmission efficiency of the original sewage data by each smart sensor fluctuates too much, the following adverse effects will occur:

[0062] The data transmission efficiency fluctuates too much, causing some data to be delayed in data analysis, affecting the real-time nature of online sewage toxicity warning. The pollutant concentration monitored in real time cannot accurately reflect the actual sewage toxicity status. The sewage toxicity warning is delayed, resulting in the inability to take emergency measures in a timely manner.

[0063] Severe transmission fluctuations lead to data packet loss or the inability of smart sensors to upload data for a long time. The missing data leads to incomplete input of the sewage toxicity assessment model, affecting the prediction results of the toxicity assessment and making it impossible to accurately judge the dynamic changes in the concentration of harmful substances.

[0064] The data transmission speeds of different smart sensors fluctuate, and the data from each smart sensor arrives at inconsistent time intervals. When fusion is performed, the data arriving at different times must be aligned or interpolated, which increases the computational complexity.

[0065] Transmission fluctuations may cause some sewage data to fail to be received, resulting in abnormal data. Abnormal data can mislead sewage toxicity warnings, trigger false alarms or missed alarms, and lead to incorrect treatment strategies, such as overdosing or misjudging the pollution source.

[0066] Sewage monitoring is carried out by multiple smart sensors in collaboration. The low transmission efficiency of some smart sensors hinders the analysis of the overall sewage data, prolongs the overall processing time, limits the ability of online collaborative analysis of sewage toxicity, and makes it difficult to calculate multivariate correlations in a timely manner;

[0067] The non-uniform data distribution caused by transmission fluctuations has a negative impact on the training of the sewage toxicity analysis model. The incomplete time series information of the training data affects the accuracy of the prediction model, and the model cannot grasp the collaborative relationship between sensors.

[0068] In order to avoid the above adverse effects, the transmission volatility information of the original sewage data transmitted by each intelligent sensor is collected, and the method for obtaining the transmission volatility coefficient based on the transmission volatility information is as follows:

[0069] The optimal range of continuous transmission is set for the transmission rate of each intelligent sensor to transmit the original sewage data, and the optimal range of continuous transmission of each intelligent sensor to transmit the original sewage data is marked as [Orf min ,Orf max ], among which Orf min is the minimum value of the optimal range of coherent transmission, Orf max is the maximum value of the optimal range for coherent transmission;

[0070] Obtain the transmission rate data of the original sewage data transmitted by each intelligent sensor within the time period T, and mark the transmission rate data of the original sewage data transmitted by each intelligent sensor within the time period T as Co t , where t is the number of the transmission rate data, and t={1,2,3…y}, where y is a positive integer;

[0071] The transmission rate data of the original sewage data transmitted by each intelligent sensor within the time period T does not belong to the optimal range of continuous transmission [Orf min ,Orf max ] transmission rate data, and marks it as not within the optimal range for coherent transmission [Orf min ,Orf max ] is the transmission rate data of the transmission volatility information Uo r , where r is not in the optimal range of coherent transmission [Orf min ,Orf max ], and r = {1, 2, 3 ... e}, where e is a positive integer;

[0072] According to the transmission volatility information Uo rGet the transmission fluctuation coefficient. The calculation expression of the transmission fluctuation coefficient is:

[0073] It should be noted that by obtaining multiple sets of transmission rate data of the original sewage data transmitted by the intelligent sensor during online sewage toxicity warning, and conducting real-time tests on the online sewage toxicity warning based on the multiple sets of transmission rate data, the minimum and maximum values ​​of the optimal range of continuous transmission are determined.

[0074] An abnormal fluctuation model is constructed by introducing the difference coefficient and the transmission fluctuation coefficient to evaluate the stability of the operating status of each intelligent sensor for sewage toxicity monitoring and generate an abnormal fluctuation coefficient;

[0075] The logic for constructing an abnormal volatility model and generating an abnormal volatility coefficient is:

[0076] After normalizing the introduced difference coefficient and the transmission fluctuation coefficient, the abnormal fluctuation model is constructed. The expression of the abnormal fluctuation model is: In the formula, Ab fl is the abnormal fluctuation coefficient, α and β are the weight coefficients of the introduced difference coefficient and the transmission fluctuation coefficient, respectively, and both α and β are positive numbers.

[0077] Data fusion is performed based on the original sewage data collected by each intelligent sensor, a fusion efficiency model is constructed to evaluate the fusion effect of the original sewage data, and a fusion efficiency index is generated;

[0078] Perform data fusion processing based on the collected data of each smart sensor and comprehensively analyze the collection parameters of each smart sensor to compensate for the time delay of a single smart sensor;

[0079] The method for data fusion based on the original sewage data collected by each intelligent sensor is:

[0080] The weighted average method is used to obtain the original sewage data after fusion. The calculation expression of the weighted average method is: Among them, Cf c is the original sewage data after fusion, w c is the weight coefficient based on the signal-to-noise ratio, Co c is the output value of the cth smart sensor, c is the number of the smart sensor, and c={1,2,3…v}, where v is a positive integer.

[0081] The method of constructing a fusion efficiency model and generating a fusion efficiency index is:

[0082] The signal-to-noise ratio of each sewage raw data before fusion is calibrated as Snr b , where b is the serial number of each sewage original data, and b = {1, 2, 3…x}, where x is a positive integer, and the signal-to-noise ratio of each sewage original data after fusion is Snf b;

[0083] The standard deviation of the original sewage data after fusion is calculated as In the formula, C va is the average value of the fused sewage data, and the calculation expression is:

[0084] Then the expression of the fusion efficiency model is In the formula, F ei is the fusion efficiency index.

[0085] Risk verification of wastewater toxicity output based on abnormal fluctuation index and fusion efficiency index;

[0086] The logic of risk verification is:

[0087] Set the abnormal fluctuation threshold Af for the abnormal fluctuation index th , set the fusion efficiency threshold Fe for the fusion efficiency index th , when the abnormal volatility index Ab fl Greater than or equal to the abnormal fluctuation threshold Af th , and the fusion efficiency index F ei Less than or equal to the fusion efficiency threshold Fe th When the signal fluctuation of the mark detection is abnormal and the data fusion is inaccurate, the management personnel are prompted to maintain each intelligent sensor and inspect the transmission line;

[0088] When the abnormal volatility index Ab fl Greater than or equal to the abnormal fluctuation threshold Af th , and the fusion efficiency index F ei Greater than the fusion efficiency threshold Fe th When the signal fluctuation is abnormal, the mark detection signal will be marked to remind the management personnel to maintain each smart sensor;

[0089] When the abnormal volatility index Ab fl Less than the abnormal fluctuation threshold Af th , and the fusion efficiency index F ei Less than or equal to the fusion efficiency threshold Fe th When the data fusion is inaccurate, the management personnel are prompted to inspect the transmission line;

[0090] When the abnormal volatility index Ab fl Less than the abnormal fluctuation threshold Af th , and the fusion efficiency index F ei Greater than the fusion efficiency threshold Fe th When doing so, the original sewage data shall be recorded and saved without prompting the management personnel.

[0091] This application evaluates the differences in the time consumption of each intelligent sensor for detecting sewage samples, as well as the differences in delays in the transmission of sewage raw data. Before data fusion processing, the delay status of the sewage raw data is comprehensively evaluated. After data fusion processing, the efficiency of data fusion is tested. Combined with data collection and data fusion, the validity of the raw sewage data is comprehensively verified, which effectively improves the accuracy of sewage toxicity warning, avoids the situation where sewage toxicity warning failure makes it difficult for managers to determine the exact fault link of the input error, improves the monitoring efficiency of sewage raw data, improves the data response timeliness of online sewage toxicity warning, and shortens the troubleshooting process of input errors.

[0092] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0093] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of computer program goods. The computer program goods include one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0094] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0095] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0096] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0097] If the functions are implemented in the form of software functional units and sold or used as independent goods, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of software goods, which are stored in a storage medium and include several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0098] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. An online sewage toxicity early warning method based on intelligent sensors, characterized in that: The specific steps include: Collect the introduced difference information of the original sewage data collected by each intelligent sensor and the transmission volatility information of the original sewage data, and obtain the introduced difference coefficient according to the introduced difference information, and obtain the transmission volatility coefficient according to the transmission volatility information; An abnormal fluctuation model is constructed by introducing the difference coefficient and the transmission fluctuation coefficient to evaluate the stability of the operating status of each intelligent sensor for sewage toxicity monitoring and generate an abnormal fluctuation coefficient; Data fusion is performed based on the original sewage data collected by each intelligent sensor, a fusion efficiency model is constructed to evaluate the fusion effect of the original sewage data, and a fusion efficiency index is generated; Risk verification of sewage toxicity output is carried out based on abnormal fluctuation index and fusion efficiency index.

2. The online sewage toxicity early warning method based on intelligent sensor according to claim 1 is characterized in that: The method for obtaining the difference information is as follows: Obtain the time consumption of the original sewage data collected by each smart sensor within the time period T, record the timestamp Ts1 of the sewage sample introduced into each smart sensor and the timestamp Ts2 of each smart sensor obtaining the original sewage data, and calculate the time consumption of the original sewage data collection as Ts c =Ts2-Ts1, where Ts c is the time consumption of collecting the original data of sewage, c is the serial number of each intelligent sensor, and c={1,2,3…v}, where v is a positive integer; Set the introduced deposition threshold to Id th , mark the time taken to collect the original sewage data as greater than or equal to the introduced sedimentation threshold Id th The data is the over-limit value Ex l , where l is the excess value Ex l , and l={1,2,3…k}, where k is a positive integer; The introduced difference information within the calculation time period T is Among them, Ex ag Ex l The average value of 3. The online sewage toxicity early warning method based on intelligent sensor according to claim 2 is characterized in that: The method for obtaining the introduced difference coefficient according to the introduced difference information is: The intelligent sensor whose original sewage data collection time exceeds the limit value within the calibration time period T is 0, and the intelligent sensor whose original sewage data collection time does not exceed the limit value within the calibration time period T is 1. The introduction sequence is generated according to the timestamp order of the sewage samples introduced by each intelligent sensor, and the introduction sequence consists of 0 and 1; The number of 0 introduced into the sequence is 0 t , the number of 1s introduced into the sequence is No t , the number of consecutive 0s between two adjacent 1s is Con t , then the calculation expression of the difference coefficient is introduced as 4. The online sewage toxicity early warning method based on intelligent sensor according to claim 1 is characterized in that: The method for collecting the transmission volatility information of the original sewage data transmitted by each intelligent sensor and obtaining the transmission volatility coefficient according to the transmission volatility information is as follows: The optimal range of continuous transmission is set for the transmission rate of each intelligent sensor to transmit the original data of sewage, and the optimal range of continuous transmission of each intelligent sensor to transmit the original data of sewage is marked as [Orf min ,Orf max ], among which, Orf min is the minimum value of the optimal range of coherent transmission, Orf max is the maximum value of the optimal range for coherent transmission; Obtain the transmission rate data of the original sewage data transmitted by each intelligent sensor within the time period T, and mark the transmission rate data of the original sewage data transmitted by each intelligent sensor within the time period T as Co t , where t is the number of the transmission rate data, and t={1,2,3…y}, where y is a positive integer; The transmission rate data of the original sewage data transmitted by each intelligent sensor within the time period T does not belong to the optimal range of continuous transmission [Orf min ,Orf max ] transmission rate data, and marks it as not within the optimal range for coherent transmission [Orf min ,Orf max ] is the transmission rate data of the transmission volatility information Uo r , where r is not in the optimal range of coherent transmission [Orf min ,Orf max ], and r = {1, 2, 3 ... e}, where e is a positive integer; According to the transmission volatility information Uo r Get the transmission fluctuation coefficient. The calculation expression of the transmission fluctuation coefficient is:

5. The online sewage toxicity early warning method based on intelligent sensor according to claim 4 is characterized in that: The logic for constructing an abnormal volatility model and generating an abnormal volatility coefficient is: After normalizing the introduced difference coefficient and the transmission fluctuation coefficient, the abnormal fluctuation model is constructed. The expression of the abnormal fluctuation model is: In the formula, Ab fl is the abnormal fluctuation coefficient, α and β are the weight coefficients of the introduced difference coefficient and the transmission fluctuation coefficient, respectively, and both α and β are positive numbers.

6. The online sewage toxicity early warning method based on intelligent sensor according to claim 1 is characterized in that: The method for data fusion based on the original sewage data collected by each intelligent sensor is: The weighted average method is used to obtain the original sewage data after fusion. The calculation expression of the weighted average method is: Among them, Cf c is the original sewage data after fusion, w c is the weight coefficient based on the signal-to-noise ratio, Co c is the output value of the cth smart sensor, c is the number of the smart sensor, and c={1,2,3…v}, where v is a positive integer.

7. The online sewage toxicity early warning method based on intelligent sensor according to claim 6 is characterized in that: The method of constructing a fusion efficiency model and generating a fusion efficiency index is: The signal-to-noise ratio of each sewage raw data before fusion is calibrated as Snr b , where b is the serial number of each sewage original data, and b = {1, 2, 3…x}, where x is a positive integer, and the signal-to-noise ratio of each sewage original data after fusion is Snf b ; The standard deviation of the original sewage data after fusion is calculated as In the formula, C va is the average value of the fused sewage data, and the calculation expression is: Then the expression of the fusion efficiency model is In the formula, F ei is the fusion efficiency index.

8. The online sewage toxicity early warning method based on intelligent sensor according to claim 7 is characterized in that: The logic of risk verification is: Set the abnormal fluctuation threshold Af for the abnormal fluctuation index th , set the fusion efficiency threshold Fe for the fusion efficiency index th , when the abnormal volatility index Ab fl Greater than or equal to the abnormal fluctuation threshold Af th , and the fusion efficiency index F ei Less than or equal to the fusion efficiency threshold Fe th When the signal fluctuation of the mark detection is abnormal and the data fusion is inaccurate, the management personnel are prompted to maintain each intelligent sensor and inspect the transmission line; When the abnormal volatility index Ab fl Greater than or equal to the abnormal fluctuation threshold Af th , and the fusion efficiency index F ei Greater than the fusion efficiency threshold Fe th When the signal fluctuation is abnormal, the mark detection signal will be marked to prompt the management personnel to perform maintenance on each smart sensor; When the abnormal volatility index Ab fl Less than the abnormal fluctuation threshold Af th , and the fusion efficiency index F ei Less than or equal to the fusion efficiency threshold Fe th When the data fusion is inaccurate, the management personnel are prompted to inspect the transmission line; When the abnormal volatility index Ab fl Less than the abnormal fluctuation threshold Af th , and the fusion efficiency index F ei Greater than the fusion efficiency threshold Fe th When doing so, the original sewage data shall be recorded and saved without prompting the management personnel.

Images