Water quality monitoring instrument fault diagnosis method, device and equipment and storage medium

Abstract

The invention discloses a water quality monitoring instrument fault diagnosis method, device and equipment and a storage medium, and relates to the technical field of water quality monitoring instrument fault diagnosis, and the method comprises the steps: obtaining actual waveform data corresponding to various monitoring parameters of a water quality monitoring instrument; obtaining standard waveform data corresponding to each piece of actual waveform data; respectively comparing the actual waveform data with the corresponding standard waveform data to obtain a comparison result; and performing fault diagnosis on the water quality monitoring instrument according to the comparison result. By applying the water quality monitoring instrument fault diagnosis method provided by the invention, the maintenance time is shortened, the operation and maintenance cost is reduced, and rapid and accurate positioning of the fault reason of the water quality monitoring instrument is realized.

Description

Technical Field

[0001] The present application relates to the technical field of fault diagnosis of water quality monitoring instruments, and in particular to a method, device, equipment and computer-readable storage medium for fault diagnosis of water quality monitoring instruments. Background Art

[0002] The online water quality monitoring system is an important part of modern environmental monitoring. Its goal is to monitor water quality in real time and accurately, and provide a scientific basis for environmental protection, water resources management and public health. As the core of the online water quality monitoring system, the performance of the online water quality monitoring instrument has a great impact on the authenticity and effectiveness of the monitoring results, and its operating status needs to be tested and diagnosed in real time.

[0003] At present, most online water quality monitoring instruments only use a single sensor to monitor absolute parameters (temperature, pressure, etc.) during operation. A threshold is set for each monitored signal. If the collected signal exceeds the threshold, the system will send an alarm signal. The accuracy of the alarm depends entirely on the sensitivity of the sensor, and the false alarm rate is high. When a water quality monitoring instrument actually fails, the water quality monitoring instrument will show various characteristics and there is no absolute threshold. At present, the main method for diagnosing faults in water quality monitoring instruments is for operation and maintenance personnel to carry tools to the site for manual troubleshooting. Troubleshooting is very time-consuming. If the operation and maintenance personnel are not experienced enough, they need to contact after-sales technicians for remote assistance, which consumes a lot of manpower costs, resulting in increased operation and maintenance costs, and the cause of the fault diagnosed is of low accuracy.

[0004] In summary, how to effectively solve the problems of the current water quality monitoring instrument fault diagnosis method being time-consuming, high operation and maintenance costs, and low accuracy of fault causes is an issue that technical personnel in this field urgently need to solve. Summary of the invention

[0005] The purpose of this application is to provide a water quality monitoring instrument fault diagnosis method, which shortens maintenance time, reduces operation and maintenance costs, and realizes rapid and accurate positioning of the cause of water quality monitoring instrument fault; another purpose of this application is to provide a water quality monitoring instrument fault diagnosis device, equipment and computer-readable storage medium.

[0006] In order to solve the above technical problems, this application provides the following technical solutions:

[0007] A water quality monitoring instrument fault diagnosis method, comprising:

[0008] Obtain the actual waveform data corresponding to various monitoring parameters of water quality monitoring instruments;

[0009] Obtaining standard waveform data corresponding to each actual waveform data;

[0010] Compare each actual waveform data with the corresponding standard waveform data to obtain a comparison result;

[0011] Fault diagnosis is performed on the water quality monitoring instrument according to the comparison result.

[0012] In a specific implementation of the present application, each actual waveform data is compared with the corresponding standard waveform data, including:

[0013] Derivative each actual waveform data respectively to obtain each first-order derivative;

[0014] Perform stationary point analysis on each first-order derivative to obtain the actual stationary point data feature set corresponding to each actual waveform data;

[0015] Obtaining standard stationary point data feature sets corresponding to each standard waveform data;

[0016] Each actual stationary point data feature set is compared with the corresponding standard stationary point data feature set.

[0017] In a specific implementation of the present application, fault diagnosis of the water quality monitoring instrument is performed according to the comparison result, including:

[0018] Determine whether there are actual stationary point feature data corresponding to each standard stationary point feature data in the corresponding standard stationary point data feature set in each actual stationary point data feature set;

[0019] If not, the fault type is determined using a pre-established fault diagnosis database; wherein the fault diagnosis database contains the corresponding relationship between each fault type, each stationary point data comparison result and each band data comparison result;

[0020] If yes, then obtain the preset stationary point data error range;

[0021] Calculate the difference array between each actual stationary point characteristic data and the corresponding standard stationary point characteristic data respectively; wherein the difference array includes the horizontal coordinate difference and the vertical coordinate difference;

[0022] Determine whether each difference array satisfies the stationary point data error range;

[0023] If not, then executing the step of using the pre-established fault diagnosis database to determine the fault type;

[0024] If so, segment each actual waveform data according to each actual stationary point feature data to obtain an actual feature band set corresponding to each actual waveform data;

[0025] Obtaining standard characteristic band sets corresponding to each standard waveform data;

[0026] By comparing each actual characteristic band set with the corresponding standard characteristic band set, fault diagnosis is performed on the water quality monitoring instrument according to the obtained comparison result.

[0027] In a specific implementation of the present application, by comparing each actual characteristic band set with the corresponding standard characteristic band set, fault diagnosis of the water quality monitoring instrument is performed according to the comparison result obtained, including:

[0028] Calculate the similarity between each actual feature band in each actual feature band set and the corresponding standard feature band in the standard feature band set respectively;

[0029] Get the preset similarity threshold;

[0030] Determine whether each similarity satisfies the similarity threshold;

[0031] If not, then executing the step of using the pre-established fault diagnosis database to determine the fault type;

[0032] If so, it is determined that the water quality monitoring instrument is operating normally.

[0033] In a specific implementation of the present application, the fault type determination is performed using a pre-established fault diagnosis database, including:

[0034] Obtaining a fuzzy diagnosis matrix pre-constructed according to the fault diagnosis database; wherein the fuzzy diagnosis matrix includes the membership of each fault cause to each fault symptom; each fault cause is obtained by analyzing the comparison results of each stationary point data and each band data in the fault diagnosis database;

[0035] Get the current comparison result vector;

[0036] Calculate a fault cause fuzzy vector according to the current comparison result vector and the fuzzy diagnosis matrix;

[0037] The fault cause fuzzy vector is used to determine the fault type.

[0038] In a specific implementation of the present application, using the fault cause fuzzy vector to determine the fault type includes:

[0039] Selecting the maximum value in the fault cause fuzzy vector;

[0040] The fault cause corresponding to the maximum value is determined as the fault cause of the water quality monitoring instrument.

[0041] In a specific implementation of the present application, the actual waveform data corresponding to various monitoring parameters of the water quality monitoring instrument are obtained, including:

[0042] Obtaining original waveform data corresponding to various monitoring parameters of the water quality monitoring instrument;

[0043] The original waveform data are filtered to obtain actual waveform data.

[0044] A water quality monitoring instrument fault diagnosis device, comprising:

[0045] The actual waveform data acquisition module is used to obtain the actual waveform data corresponding to various monitoring parameters of the water quality monitoring instrument;

[0046] A standard waveform data acquisition module is used to acquire the standard waveform data corresponding to each actual waveform data;

[0047] A comparison result obtaining module is used to compare each actual waveform data with the corresponding standard waveform data to obtain a comparison result;

[0048] A fault diagnosis module is used to perform fault diagnosis on the water quality monitoring instrument according to the comparison result.

[0049] A water quality monitoring instrument fault diagnosis device, comprising:

[0050] Memory for storing computer programs;

[0051] A processor is used to implement the steps of the water quality monitoring instrument fault diagnosis method as described above when executing the computer program.

[0052] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the water quality monitoring instrument fault diagnosis method as described above.

[0053] The water quality monitoring instrument fault diagnosis method provided in the present application obtains actual waveform data corresponding to various monitoring parameters of the water quality monitoring instrument; obtains standard waveform data corresponding to each actual waveform data; compares each actual waveform data with the corresponding standard waveform data to obtain a comparison result; and diagnoses the water quality monitoring instrument fault according to the comparison result.

[0054] It can be seen from the above technical solution that by obtaining the actual waveform data corresponding to each monitoring parameter of the water quality monitoring instrument, and obtaining the standard waveform data corresponding to each actual waveform data, each actual waveform data is compared with the corresponding standard waveform data, and the water quality monitoring instrument is diagnosed according to the comparison results. Comprehensive and integrated monitoring of water quality monitoring instruments is achieved, which can timely discover hidden faults, reduce the false alarm and missed alarm rate of equipment abnormalities, and reduce the occurrence of maintenance events. The cause of the failure of the water quality monitoring instrument is quickly and accurately located, which improves the operation and maintenance efficiency of the water quality monitoring instrument, shortens the maintenance time, saves human resources, and reduces the operation and maintenance costs.

[0055] Correspondingly, the present application also provides a water quality monitoring instrument fault diagnosis device, equipment and computer-readable storage medium corresponding to the above-mentioned water quality monitoring instrument fault diagnosis method, which has the above-mentioned technical effects and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0057] FIG1 is a flow chart of an implementation method of a water quality monitoring instrument fault diagnosis method in an embodiment of the present application;

[0058] FIG2 is another implementation flow chart of the method for diagnosing a fault in a water quality monitoring instrument in an embodiment of the present application;

[0059] FIG3 is a temperature-time curve diagram of a digestion cup in an embodiment of the present application;

[0060] FIG4 is a structural block diagram of a water quality monitoring instrument fault diagnosis device according to an embodiment of the present application;

[0061] FIG5 is a structural block diagram of a water quality monitoring instrument fault diagnosis device in an embodiment of the present application;

[0062] FIG6 is a schematic diagram of the specific structure of a water quality monitoring instrument fault diagnosis device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0063] In order to enable those skilled in the art to better understand the present application, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present application.

[0064] Referring to FIG. 1 , FIG. 1 is a flow chart of an implementation method of a water quality monitoring instrument fault diagnosis method in an embodiment of the present application. The method may include the following steps:

[0065] S101: Obtain actual waveform data corresponding to various monitoring parameters of the water quality monitoring instrument.

[0066] Use water quality monitoring instruments to monitor various monitoring parameters of the sample in advance, and draw actual waveform data for the actual data monitored by each type of monitoring parameter. Obtain the actual waveform data corresponding to each type of monitoring parameter of the water quality monitoring instrument.

[0067] Various monitoring parameters may include digestion cup temperature, colorimetric channel light emitting diode (LED) light intensity, photoelectric measurement channel signal, etc.

[0068] S102: Obtaining standard waveform data corresponding to each actual waveform data.

[0069] The standard waveform data corresponding to each monitoring parameter are constructed in advance, and after the actual waveform data corresponding to each monitoring parameter of the water quality monitoring instrument are obtained, the standard waveform data corresponding to each actual waveform data are obtained.

[0070] S103: Compare each actual waveform data with the corresponding standard waveform data to obtain a comparison result.

[0071] After obtaining the actual waveform data and standard waveform data corresponding to each monitoring parameter, the actual waveform data is compared with the corresponding standard waveform data to obtain a comparison result. For example, the stationary point data can be compared, and each band of the entire waveform data can be compared.

[0072] S104: Perform fault diagnosis on the water quality monitoring instrument according to the comparison result.

[0073] After comparing each actual waveform data with the corresponding standard waveform data and obtaining the comparison results, the water quality monitoring instrument is diagnosed for faults according to the comparison results. For example, the fault diagnosis can be performed by analyzing whether there is a lack of stationary points, or by analyzing whether the similarity between each actual band and the corresponding standard band is greater than a preset threshold.

[0074] It can be seen from the above technical solution that by obtaining the actual waveform data corresponding to each monitoring parameter of the water quality monitoring instrument, and obtaining the standard waveform data corresponding to each actual waveform data, each actual waveform data is compared with the corresponding standard waveform data, and the water quality monitoring instrument is diagnosed according to the comparison results. Comprehensive and integrated monitoring of water quality monitoring instruments is achieved, which can timely discover hidden faults, reduce the false alarm and missed alarm rate of equipment abnormalities, and reduce the occurrence of maintenance events. The cause of the failure of the water quality monitoring instrument is quickly and accurately located, which improves the operation and maintenance efficiency of the water quality monitoring instrument, shortens the maintenance time, saves human resources, and reduces the operation and maintenance costs.

[0075] It should be noted that, based on the above embodiments, the embodiments of the present application also provide corresponding improved solutions. In the subsequent embodiments, the same steps or corresponding steps as those in the above embodiments can be referenced to each other, and the corresponding beneficial effects can also be referenced to each other, which will not be repeated one by one in the following improved embodiments.

[0076] Referring to FIG. 2 , FIG. 2 is another implementation flow chart of the method for diagnosing a fault in a water quality monitoring instrument in an embodiment of the present application. The method may include the following steps:

[0077] S201: Obtaining original waveform data corresponding to various monitoring parameters of the water quality monitoring instrument.

[0078] The monitoring time range for each monitoring parameter can be pre-set to obtain the monitoring parameters corresponding to each time point within the monitoring time range. After obtaining the monitoring parameters, the original waveform data is drawn according to the obtained monitoring parameters. The original waveform data corresponding to the monitoring parameters of the water quality monitoring instrument are obtained.

[0079] S202: Filter each original waveform data to obtain each actual waveform data.

[0080] After obtaining the original waveform data corresponding to various monitoring parameters of the water quality monitoring instrument, since the lines of each original waveform data may not be smooth, each original waveform data is filtered, such as Savitzky-Golay adaptive digital filtering, to obtain each actual waveform data. By filtering each original waveform data, the actual waveform data finally obtained is smoother, reducing interference information such as background noise, avoiding the influence of some accidental fluctuation parameter points on the subsequent waveform data stationary point analysis, improving the quality of the waveform data, and thus improving the accuracy of fault diagnosis of water quality monitoring instruments.

[0081] The following filtering algorithm formula can be used to filter the original waveform data:

[0082] ;

[0083] in, is the filtered data, is the original value, is the coefficient for filtering the i-th value, m is the width of half the filter window, and N is the filter length, which is equal to the width of the sliding array 2m+1.

[0084] S203: Obtaining the standard waveform data corresponding to each actual waveform data.

[0085] S204: Deriving each actual waveform data respectively to obtain each first-order derivative.

[0086] After filtering each original waveform data to obtain each actual waveform data, each actual waveform data is differentiated to obtain each first-order derivative.

[0087] The actual waveform data can be derived using the following formula:

[0088] ;

[0089] in, is the original data, is the derivative.

[0090] S205: Perform stationary point analysis on each first-order derivative to obtain actual stationary point data feature sets corresponding to each actual waveform data.

[0091] After differentiating each actual waveform data to obtain each first-order derivative, stationary point analysis is performed on each first-order derivative to obtain an actual stationary point data feature set corresponding to each actual waveform data.

[0092] S206: Obtaining standard stationary point data feature sets corresponding to each standard waveform data.

[0093] The standard stationary point data feature sets corresponding to the respective standard waveform data are preset, and the standard stationary point data feature sets corresponding to the respective standard waveform data are obtained.

[0094] S207: Compare each actual stationary point data feature set with the corresponding standard stationary point data feature set to obtain a comparison result.

[0095] After obtaining the actual stationary point data feature sets corresponding to each actual waveform data and obtaining the standard stationary point data feature sets corresponding to each standard waveform data, each actual stationary point data feature set is compared with the corresponding standard stationary point data feature set, such as comparing the horizontal coordinate of the actual stationary point in each actual stationary point data feature set with the horizontal coordinate of the standard stationary point in the corresponding standard stationary point data feature set, and comparing the vertical coordinate of the actual stationary point in each actual stationary point data feature set with the vertical coordinate of the standard stationary point in the corresponding standard stationary point data feature set to obtain a comparison result.

[0096] S208: Determine whether each actual stationary point data feature set contains actual stationary point feature data corresponding to each standard stationary point feature data in the corresponding standard stationary point data feature set; if not, execute step S209; if yes, execute step S210.

[0097] After comparing each actual stationary point data feature set with the corresponding standard stationary point data feature set and obtaining the comparison results, determine whether each actual stationary point feature set contains actual stationary point feature data corresponding to each standard stationary point feature data in the standard stationary point data feature set. If not, it means that there is a fault in the water quality monitoring instrument, and step S209 is executed. If so, it means that the water quality monitoring instrument can currently function in each monitoring stage corresponding to each type of monitoring parameter, and step S210 is executed.

[0098] S209: Determine the fault type using a pre-established fault diagnosis database.

[0099] The fault diagnosis database includes the corresponding relationship between each fault type, each stationary point data comparison result and each band data comparison result.

[0100] A fault diagnosis database is pre-built that contains the corresponding relationships between each fault type, each stationary point data comparison result, and each band data comparison result. When it is determined that there is actual stationary point feature data corresponding to a certain standard stationary point feature data in the corresponding standard stationary point data feature set that is missing in the actual stationary point data feature set, it indicates that there is a fault in the water quality monitoring instrument, and the fault type is determined using the pre-established fault diagnosis database. The stationary point feature data is analyzed through the pre-established fault diagnosis database, and the fault type is determined based on the stationary point feature data, thereby realizing the rapid and accurate positioning of the cause of the water quality monitoring instrument failure.

[0101] In a specific implementation of the present application, step S209 may include the following steps:

[0102] Step 1: Obtain a fuzzy diagnosis matrix pre-constructed according to a fault diagnosis database; wherein the fuzzy diagnosis matrix includes the degree of membership of each fault cause to each fault symptom; each fault cause is obtained by analyzing the comparison results of each stationary point data and each band data in the fault diagnosis database;

[0103] Step 2: Get the current comparison result vector;

[0104] Step 3: Calculate the fault cause fuzzy vector based on the current comparison result vector and the fuzzy diagnosis matrix;

[0105] Step 4: Use the fault cause fuzzy vector to determine the fault type.

[0106] For the convenience of description, the above four steps can be combined for explanation.

[0107] By analyzing the comparison results of each stationary point data and each band data in the fault diagnosis database in advance, the causes of each fault are obtained, and a fuzzy diagnosis matrix including the membership of each fault cause to each fault sign is pre-constructed. Obtain the fuzzy diagnosis matrix pre-constructed according to the fault diagnosis database, obtain the current comparison result vector, calculate the fuzzy vector of the fault cause according to the current comparison result vector and the fuzzy diagnosis matrix, and use the fuzzy vector of the fault cause to determine the fault type. Fuzzy diagnosis is to judge the fault according to the symptoms observed during the operation of the water quality monitoring instrument. Since this diagnostic method is more in line with human thinking and can overcome the difficulties brought about by the complexity of machinery and equipment, it has a strong practical value. By using the pre-constructed fuzzy diagnosis matrix to calculate the fuzzy vector of the fault cause, the fuzzy vector of the fault cause calculated can be used to quickly and accurately locate the fault cause of the water quality monitoring instrument, provide guidance for the operation status of the instrument, and achieve the purpose of early prediction, so as to timely discover the hidden dangers of faults, reduce the false alarm and missed alarm rate of abnormal facilities, and reduce the occurrence of maintenance events.

[0108] Suppose all possible causes of failure in a system (water quality monitoring instrument or a subsystem) are the fault cause set, such as main control board failure, multi-way valve failure, precision metering pump failure, heating wire fuse, reagent liquid shortage, etc., represented by the vector fault cause set Y=[y1, y2,...,yn], where n represents the total number of system fault cause types; suppose the fault symptoms that may be caused by the fault causes are the fault symptom set, such as abnormal temperature rise, abnormal temperature drop, abnormal drainage, abnormal blank light intensity, abnormal color light intensity, etc., represented by the vector X=[x1, x2,...,xm], where m represents the total number of fault symptom types.

[0109] There is an intricate fuzzy relationship between the fault causes and fault symptoms of water quality online monitoring instruments. The same fault symptom may be caused by multiple fault causes, and the same fault cause may cause multiple fault symptoms. Fault judgment is made on the fault cause yj (j=1, 2,..., n) in the fault cause set Y, and the membership of the fault cause to the fault symptom xi (i=1, 2,..., m) or the credibility rij of the fault cause yj when the symptom xi occurs is determined. The larger the rij, the greater the role of the fault cause yj in the occurrence of the fault symptom phenomenon xi, that is, the greater the correlation between the two; the evaluation set of n fault causes corresponding to m fault symptoms constitutes the fuzzy diagnosis matrix R, which can be expressed by the following formula:

[0110] ;

[0111] Among them, 0 ≤ rij ≤ 1, 1 ≤ i ≤ m, 1 ≤ j ≤ n, R represents a fuzzy relationship from fault symptom X to fault cause Y; the reliability of rij determines the quality and success of the diagnosis result, and its initial value can be comprehensively evaluated based on methods such as fuzzy diagnosis matrix and expert statistics, and can also be gradually modified and improved through supervised training and machine learning.

[0112] After fuzzy operation Y=X×R, the fuzzy vector of the fault cause Y=[y1, y2, …, yn] is obtained. Arrange yj from large to small, and it is considered that the target to be diagnosed is most likely to have the largest membership, followed by the second largest membership, and so on. Finally, the diagnosis result is output according to the size of the fault cause membership.

[0113] As shown in Figure 3, taking the temperature curve as an example, common fault causes are simulated and the digestion cup temperature is collected to establish a fault diagnosis database as follows (only part of it is listed, not exhaustive):

[0114] 1) Fault symptom: abnormal heating.

[0115] Cause of failure: The heater resistor is blown, the heater power supply circuit is broken, or the heater terminal has poor contact;

[0116] Stationary point data features: The stationary point feature data are T0 and T5 feature points, and the T1, T2, T3, and T4 feature points are missing;

[0117] Band data characteristics: No band characteristic data.

[0118] 2) Fault symptoms: abnormal cooling.

[0119] Causes of the failure: The cooling fan is damaged, the cooling fan power supply circuit is broken, the cooling fan terminal has poor contact, the cooling fan blades are stuck with foreign objects;

[0120] Stationary point data characteristics: The stationary point characteristic data are T0, T1, T2, T3, T4, T5, and each point is within the set threshold range;

[0121] Band data characteristics: The fitting degrees of the T0-T1, T1-T2, and T3-T4 bands are within the set threshold range, while the fitting degrees of the T2-T3 and T4-T5 bands are beyond the set threshold range;

[0122] Analyze the test curves and compare them to determine which fault signs exist. According to the principle of taking 1 if the fault sign appears and taking 0 if it does not appear, if the temperature rise abnormality (x1) appears and the temperature drop abnormality (x2) does not appear, the fault sign set is: X=[x1, x2]=[1 0]

[0123] By statistically analyzing a large amount of fault diagnosis case data collected on abnormal temperature curves of water quality monitoring instruments, the specific percentage value (i.e., membership degree or weight coefficient) of the possibility that a fault symptom is caused by a certain fault cause is determined.

[0124] As shown in Table 1, Table 1 is a corresponding relationship table of fault symptoms and fault cause sets of abnormal temperature curves.

[0125] Table 1

[0126]

[0127] According to Table 1, its fuzzy relationship matrix is:

[0128] ;

[0129] Therefore, the cause of the failure is:

[0130] Y=X×R= × = ;

[0131] Among them, the third item is the largest, which is 0.8, that is, the total value of the membership of various relevant signs corresponding to y3 is the largest. Based on this, it can be determined that the cause of the fault is y3, that is, the poor contact of the heater terminal.

[0132] In a specific implementation of the present application, using the fault cause fuzzy vector to determine the fault type may include the following steps:

[0133] Step 1: Select the maximum value in the fuzzy vector of the fault cause;

[0134] Step 2: Determine the fault cause corresponding to the maximum value as the fault cause of the water quality monitoring instrument.

[0135] For the convenience of description, the above two steps can be combined for explanation.

[0136] After the fuzzy vector of the fault cause is calculated, the maximum value in the fuzzy vector of the fault cause is selected, and the fault cause corresponding to the maximum value is determined as the fault cause of the water quality monitoring instrument. By determining the fault cause corresponding to the maximum value in the fuzzy vector of the fault cause as the fault cause of the water quality monitoring instrument, the fault cause of the water quality monitoring instrument is quickly and accurately located.

[0137] S210: Obtaining a preset stationary point data error range.

[0138] The stationary point data error range is preset, such as the stationary point horizontal coordinate error range and the stationary point vertical coordinate error range can be preset separately, and the stationary point horizontal coordinate error range and the stationary point vertical coordinate error range can also be set to a unified value. When it is determined that there are actual stationary point feature data corresponding to each standard stationary point feature data in the corresponding standard stationary point data feature set in each actual stationary point data feature set, it means that the water quality monitoring instrument can currently function for each monitoring stage corresponding to each type of monitoring parameter, and obtain the preset stationary point data error range.

[0139] S211: Calculate the difference arrays of each actual stationary point feature data and the corresponding standard stationary point feature data respectively.

[0140] The difference array includes the horizontal coordinate difference and the vertical coordinate difference.

[0141] After obtaining the actual stationary point data feature sets corresponding to each actual waveform data and obtaining the standard stationary point data feature sets corresponding to each standard waveform data, the difference arrays of each actual stationary point feature data and the corresponding standard stationary point feature data are calculated respectively, and the difference arrays include the horizontal coordinate difference and the vertical coordinate difference.

[0142] S212: Determine whether each difference array satisfies the stationary point data error range. If not, return to step S209. If yes, execute step S213.

[0143] After respectively calculating the difference arrays between each actual stationary point characteristic data and the corresponding standard stationary point characteristic data, it is determined whether each difference array satisfies the stationary point data error range. For example, it can be determined whether the absolute value of the horizontal coordinate difference and the absolute value of the vertical coordinate difference in each difference array satisfy the stationary point data error range. If not, it indicates that there is a fault in the water quality monitoring instrument. The fault type is determined using a pre-established fault diagnosis database. If so, it indicates that the water quality monitoring instrument can currently function in each monitoring stage corresponding to each type of monitoring parameter, and step S213 is executed.

[0144] See Figure 3, which is a temperature-time curve of a digestion cup in an embodiment of the present application. The process of determining whether each difference array satisfies the stationary point data error range may include the following steps:

[0145] 1) Taking the waveform data points as the original values, calculate the derivative between every two adjacent points;

[0146] 2) Based on the data from step 1), the 0-point data is used as the measurement start time point T0, and compared with the standard T0 time point to determine whether the error is within the normal range;

[0147] 3) Based on the data from step 1), the end point data is the measurement end time point T5, which is compared with the standard time point T5 to determine whether the error is within the normal range;

[0148] 4) According to the T0 and T5 time points in step 2) and step 3), take T0 as the starting point and T5 as the end point to determine the derivative values. When the value changes from 0 to positive, the sample digestion begins. The digestion heating start time point T1 is compared with the standard T1 time point to determine whether the error is within the normal range;

[0149] 5) Take T1 as the starting point and T5 as the end point, and judge the derivative value of each point. When the value changes from 0 to negative, the sample digestion is completed. The digestion heating is turned off and the cooling fan is turned on at time point T2. Compare with the standard time point T2 to determine whether the error is within the normal range;

[0150] 6) Take T2 as the starting point and T5 as the end point, and judge the derivative values. When the value changes from 0 to positive, the color reaction begins. The color heating is turned on at time T3. Compare it with the standard time T3 to determine whether the error is within the normal range;

[0151] 7) Take T3 as the starting point and T5 as the end point, and judge the derivative value of each point. When the value changes from 0 to negative, the color development reaction of the sample ends, the color development heating is turned off, and the cooling fan is turned on at time point T4. Compare with the standard time point T4 to determine whether the error is within the normal range;

[0152] 8) If all stationary point data feature points from T0 to T5 are not obtained, fuzzy diagnostic analysis can be performed to obtain the current instrument operating status.

[0153] S213: Segment each actual waveform data according to each actual stationary point feature data to obtain an actual feature band set corresponding to each actual waveform data.

[0154] After determining that each difference array meets the error range of the stationary point data, it means that the water quality monitoring instrument can currently function in each monitoring stage corresponding to each monitoring parameter. According to each actual stationary point characteristic data, each actual waveform data is segmented to obtain the actual characteristic band set corresponding to each actual waveform data.

[0155] S214: Obtain standard feature band sets corresponding to each standard waveform data.

[0156] Each standard waveform data is divided into bands in advance, and a standard characteristic band set corresponding to each standard waveform data is obtained.

[0157] S215: By comparing each actual characteristic band set with the corresponding standard characteristic band set, fault diagnosis is performed on the water quality monitoring instrument according to the comparison result.

[0158] After obtaining the actual feature band sets corresponding to each actual waveform data in segments, and obtaining the standard feature band sets corresponding to each standard waveform data, each actual feature band set is compared with the corresponding standard feature band set, and the water quality monitoring instrument is diagnosed for faults based on the comparison results. By comparing each actual waveform data with the corresponding standard waveform data in segments, an accurate comparison of each actual waveform data with the corresponding standard waveform data is achieved, further improving the accuracy of fault diagnosis for water quality monitoring instruments. By performing a multi-dimensional comparison of actual waveform data and standard waveform data, the accuracy of fault location for water quality monitoring instruments is enhanced, and the possible fault risks of water quality monitoring instruments can be effectively predicted to remind operation and maintenance personnel to strengthen prevention and ensure the safe and reliable operation of water quality monitoring instruments.

[0159] In a specific implementation of the present application, step S215 may include the following steps:

[0160] Step 1: Calculate the similarity between each actual feature band in each actual feature band set and the corresponding standard feature band in the standard feature band set;

[0161] Step 2: Obtain a preset similarity threshold;

[0162] Step 3: Determine whether all similarities meet the similarity threshold, if not, return to step S209, if yes, go to step 4;

[0163] Step 4: Make sure the water quality monitoring instrument is operating normally.

[0164] For the convenience of description, the above four steps can be combined for explanation.

[0165] After obtaining the actual feature band sets corresponding to each actual waveform data in segments and obtaining the standard feature band sets corresponding to each standard waveform data, respectively calculate the similarity between each actual feature band in each actual feature band set and the standard feature band in the corresponding standard feature band set, obtain the preset similarity threshold, and determine whether each similarity satisfies the similarity threshold. If not, it means that there is a fault in the water quality monitoring instrument. The fault type is determined using the pre-established fault diagnosis database. If so, it is determined that the water quality monitoring instrument is operating normally. By calculating the similarity between each actual waveform data and the corresponding standard waveform data, and comparing the calculated similarity with the preset similarity threshold, an accurate quantitative comparison of each actual waveform data and the corresponding standard waveform data is achieved, further improving the accuracy of fault diagnosis of water quality monitoring instruments.

[0166] The similarity between each actual feature band in each actual feature band set and the corresponding standard feature band in the standard feature band set can be calculated according to the following formula:

[0167] ;

[0168] Where r is the Pearson correlation coefficient, -1 ≤ r ≤ 1; is the value of the i-th variable x; is the value of the i-th variable y; is the average value of n variable x; is the average of the n y values.

[0169] As shown in FIG3 , the process of determining whether each similarity satisfies the similarity threshold may include the following steps:

[0170] 1) Taking T0 as the starting point and T1 as the end point, i.e. the first characteristic band, the similarity between the first characteristic band and the standard characteristic band is calculated according to the above similarity calculation formula, and the similarity is compared to determine whether it is within the normal range;

[0171] 2) Taking T1 as the starting point and T2 as the end point, i.e. the second characteristic band, the similarity between the second characteristic band and the standard characteristic band is calculated according to the above similarity calculation formula, and the similarity is compared to determine whether it is within the normal range;

[0172] 3) Taking T2 as the starting point and T3 as the end point, i.e. the third characteristic band, the similarity between the third characteristic band and the standard characteristic band is calculated according to the above similarity calculation formula, and the similarity is compared to determine whether it is within the normal range;

[0173] 4) Taking T3 as the starting point and T4 as the end point, i.e. the fourth characteristic band, the similarity between the fourth characteristic band and the standard characteristic band is calculated according to the above similarity calculation formula, and the similarity is compared to determine whether it is within the normal range;

[0174] 5) Taking T4 as the starting point and T5 as the end point, i.e. the fifth characteristic band, the similarity between the fifth characteristic band and the standard characteristic band is calculated according to the above similarity calculation formula, and the similarity is compared to determine whether it is within the normal range;

[0175] 6) Through fuzzy diagnostic analysis, the current operating status of the instrument can be obtained.

[0176] By introducing band division and making similarity judgments on each band respectively, the overall trend of the characteristic band can be evaluated, avoiding the one-sidedness of judging only at individual time points.

[0177] Corresponding to the above method embodiments, the present application also provides a water quality monitoring instrument fault diagnosis device. The water quality monitoring instrument fault diagnosis device described below and the water quality monitoring instrument fault diagnosis method described above can be referenced to each other.

[0178] Referring to FIG. 4 , FIG. 4 is a structural block diagram of a water quality monitoring instrument fault diagnosis device in an embodiment of the present application, and the device may include:

[0179] The actual waveform data acquisition module 41 is used to acquire the actual waveform data corresponding to various monitoring parameters of the water quality monitoring instrument;

[0180] The standard waveform data acquisition module 42 is used to acquire the standard waveform data corresponding to each actual waveform data;

[0181] A comparison result obtaining module 43 is used to compare each actual waveform data with the corresponding standard waveform data to obtain a comparison result;

[0182] The fault diagnosis module 44 is used to perform fault diagnosis on the water quality monitoring instrument according to the comparison result.

[0183] It can be seen from the above technical solution that by obtaining the actual waveform data corresponding to each monitoring parameter of the water quality monitoring instrument, and obtaining the standard waveform data corresponding to each actual waveform data, each actual waveform data is compared with the corresponding standard waveform data, and the water quality monitoring instrument is diagnosed according to the comparison results. Comprehensive and integrated monitoring of water quality monitoring instruments is achieved, which can timely discover hidden faults, reduce the false alarm and missed alarm rate of equipment abnormalities, and reduce the occurrence of maintenance events. The cause of the failure of the water quality monitoring instrument is quickly and accurately located, which improves the operation and maintenance efficiency of the water quality monitoring instrument, shortens the maintenance time, saves human resources, and reduces the operation and maintenance costs.

[0184] In a specific implementation of the present application, the comparison result obtaining module 43 includes:

[0185] The first-order derivative obtaining submodule is used to respectively derive each actual waveform data to obtain each first-order derivative;

[0186] The actual stationary point data feature set acquisition submodule is used to perform stationary point analysis on each first-order derivative to obtain the actual stationary point data feature set corresponding to each actual waveform data;

[0187] A standard stationary point data feature set acquisition submodule is used to acquire the standard stationary point data feature sets corresponding to each standard waveform data;

[0188] The stationary point data feature set comparison submodule is used to compare each actual stationary point data feature set with the corresponding standard stationary point data feature set.

[0189] In a specific implementation of the present application, the fault diagnosis module 44 includes:

[0190] The first judgment submodule is used to judge whether there are actual stationary point feature data corresponding to each standard stationary point feature data in the corresponding standard stationary point data feature set in each actual stationary point data feature set;

[0191] The fault type determination submodule is used to determine the fault type using a pre-established fault diagnosis database when it is determined that the actual stationary point feature data corresponding to each standard stationary point feature data in the corresponding standard stationary point data feature set do not all exist in each actual stationary point data feature set; wherein the fault diagnosis database contains the corresponding relationship between each fault type, each stationary point data comparison result and each band data comparison result;

[0192] A stationary point data error range acquisition submodule is used to acquire a preset stationary point data error range when it is determined that actual stationary point feature data corresponding to each standard stationary point feature data in the corresponding standard stationary point data feature set exists in each actual stationary point data feature set;

[0193] The difference array calculation submodule is used to calculate the difference array between each actual stationary point feature data and the corresponding standard stationary point feature data; wherein the difference array includes the horizontal coordinate difference and the vertical coordinate difference;

[0194] The second judgment submodule is used to judge whether each difference array satisfies the stationary point data error range;

[0195] The fault type determination submodule is further used to determine the fault type using a pre-established fault diagnosis database when it is determined that there is a difference array in each difference array that does not meet the stationary point data error range;

[0196] The actual feature band set acquisition submodule is used to segment each actual waveform data according to each actual stationary point feature data when it is determined that each difference array satisfies the stationary point data error range, so as to obtain the actual feature band set corresponding to each actual waveform data;

[0197] The standard characteristic band set acquisition submodule is used to acquire the standard characteristic band sets corresponding to each standard waveform data;

[0198] The fault diagnosis submodule is used to compare each actual characteristic band set with the corresponding standard characteristic band set, and perform fault diagnosis on the water quality monitoring instrument according to the comparison result obtained.

[0199] In a specific implementation of the present application, the fault diagnosis submodule includes:

[0200] A similarity calculation unit, used for respectively calculating the similarity between each actual feature band in each actual feature band set and a corresponding standard feature band in the standard feature band set;

[0201] A similarity threshold acquisition unit, used to acquire a preset similarity threshold;

[0202] A first judging unit, used to judge whether each similarity satisfies a similarity threshold;

[0203] A fault type determination unit, configured to determine the fault type using a pre-established fault diagnosis database when it is determined that there is a similarity among the similarities that does not meet a similarity threshold;

[0204] The normal operation status determination unit is used to determine that the operation status of the water quality monitoring instrument is normal when it is determined that all similarities meet the similarity threshold.

[0205] In a specific implementation of the present application, the fault type determination submodule includes:

[0206] A fuzzy diagnosis matrix acquisition unit is used to acquire a fuzzy diagnosis matrix pre-constructed according to a fault diagnosis database; wherein the fuzzy diagnosis matrix includes the membership degree of each fault cause to each fault symptom; each fault cause is obtained by analyzing the comparison results of each stationary point data and each band data in the fault diagnosis database;

[0207] A current comparison result vector acquisition unit, used to acquire a current comparison result vector;

[0208] A fault cause fuzzy vector calculation unit, used for calculating the fault cause fuzzy vector according to the current comparison result vector and the fuzzy diagnosis matrix;

[0209] The fault type determination unit is used to determine the fault type using the fault cause fuzzy vector.

[0210] In a specific implementation of the present application, the fault type determination unit includes:

[0211] The maximum value selection subunit is used to select the maximum value in the fuzzy vector of the fault cause;

[0212] The fault cause determination subunit is used to determine the fault cause corresponding to the maximum value as the fault cause of the water quality monitoring instrument.

[0213] In a specific implementation of the present application, the actual waveform data acquisition module 41 includes:

[0214] The original waveform data acquisition submodule is used to obtain the original waveform data corresponding to various monitoring parameters of the water quality monitoring instrument;

[0215] The actual waveform data acquisition submodule is used to perform filtering processing on each original waveform data to obtain each actual waveform data.

[0216] Corresponding to the above method embodiment, referring to FIG5 , FIG5 is a schematic diagram of a water quality monitoring instrument fault diagnosis device provided by the present application, and the device may include:

[0217] A memory 332, for storing computer programs;

[0218] The processor 322 is used to implement the steps of the water quality monitoring instrument fault diagnosis method of the above method embodiment when executing the computer program.

[0219] Specifically, please refer to Figure 6, which is a specific structural diagram of a water quality monitoring instrument fault diagnosis device provided in this embodiment. The water quality monitoring instrument fault diagnosis device may have relatively large differences due to different configurations or performances, and may include a processor (central processing units, CPU) 322 (for example, one or more processors) and a memory 332, and the memory 332 stores one or more computer programs 342 or data 344. Among them, the memory 332 can be a temporary storage or a permanent storage. The program stored in the memory 332 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations in the data processing device. Furthermore, the processor 322 can be configured to communicate with the memory 332 to execute a series of instruction operations in the memory 332 on the water quality monitoring instrument fault diagnosis device 301.

[0220] The water quality monitoring instrument fault diagnosis device 301 may also include one or more power supplies 326 , one or more wired or wireless network interfaces 350 , one or more input and output interfaces 358 , and / or one or more operating systems 341 .

[0221] The steps in the water quality monitoring instrument fault diagnosis method described above can be implemented by the structure of the water quality monitoring instrument fault diagnosis device.

[0222] Corresponding to the above method embodiment, the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the following steps can be implemented:

[0223] Obtain actual waveform data corresponding to various monitoring parameters of the water quality monitoring instrument; obtain standard waveform data corresponding to each actual waveform data; compare each actual waveform data with the corresponding standard waveform data to obtain a comparison result; and perform fault diagnosis on the water quality monitoring instrument according to the comparison result.

[0224] The computer-readable storage medium may include: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0225] For an introduction to the computer-readable storage medium provided in this application, please refer to the above method embodiment, and this application will not go into details here.

[0226] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the devices, equipment and computer-readable storage media disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0227] Specific examples are used herein to illustrate the principles and implementation methods of the present application, and the description of the above embodiments is only used to help understand the technical solution and core ideas of the present application. It should be pointed out that for ordinary technicians in this technical field, without departing from the principles of the present application, several improvements and modifications can be made to the present application, and these improvements and modifications also fall within the scope of protection of the present application.

Claims

1. A water quality monitoring instrument fault diagnosis method, characterized in that: include: Obtain the actual waveform data corresponding to various monitoring parameters of water quality monitoring instruments; Obtaining standard waveform data corresponding to each actual waveform data; Compare each actual waveform data with the corresponding standard waveform data to obtain a comparison result; Fault diagnosis is performed on the water quality monitoring instrument according to the comparison result.

2. The water quality monitoring instrument fault diagnosis method according to claim 1, characterized in that: Compare each actual waveform data with the corresponding standard waveform data, including: Derivative each actual waveform data respectively to obtain each first-order derivative; Perform stationary point analysis on each first-order derivative to obtain the actual stationary point data feature set corresponding to each actual waveform data; Obtaining standard stationary point data feature sets corresponding to each standard waveform data; Each actual stationary point data feature set is compared with the corresponding standard stationary point data feature set.

3. The water quality monitoring instrument fault diagnosis method according to claim 2, characterized in that: Performing fault diagnosis on the water quality monitoring instrument according to the comparison result includes: Determine whether there are actual stationary point feature data corresponding to each standard stationary point feature data in the corresponding standard stationary point data feature set in each actual stationary point data feature set; If not, the fault type is determined using a pre-established fault diagnosis database; wherein the fault diagnosis database contains the corresponding relationship between each fault type, each stationary point data comparison result and each band data comparison result; If yes, then obtain the preset stationary point data error range; Calculate the difference array between each actual stationary point characteristic data and the corresponding standard stationary point characteristic data respectively; wherein the difference array includes the horizontal coordinate difference and the vertical coordinate difference; Determine whether each difference array satisfies the stationary point data error range; If not, then executing the step of using the pre-established fault diagnosis database to determine the fault type; If so, segment each actual waveform data according to each actual stationary point feature data to obtain an actual feature band set corresponding to each actual waveform data; Obtaining standard characteristic band sets corresponding to each standard waveform data; By comparing each actual characteristic band set with the corresponding standard characteristic band set, fault diagnosis is performed on the water quality monitoring instrument according to the obtained comparison result.

4. The water quality monitoring instrument fault diagnosis method according to claim 3, characterized in that: By comparing each actual characteristic band set with the corresponding standard characteristic band set, fault diagnosis of the water quality monitoring instrument is performed according to the comparison result, including: Calculate the similarity between each actual feature band in each actual feature band set and the corresponding standard feature band in the standard feature band set respectively; Get the preset similarity threshold; Determine whether each similarity satisfies the similarity threshold; If not, then executing the step of using the pre-established fault diagnosis database to determine the fault type; If so, it is determined that the water quality monitoring instrument is operating normally.

5. The water quality monitoring instrument fault diagnosis method according to claim 3 or 4, characterized in that: Use the pre-established fault diagnosis database to determine the fault type, including: Obtaining a fuzzy diagnosis matrix pre-constructed according to the fault diagnosis database; wherein the fuzzy diagnosis matrix includes the membership of each fault cause to each fault symptom; each fault cause is obtained by analyzing the comparison results of each stationary point data and each band data in the fault diagnosis database; Get the current comparison result vector; Calculate a fault cause fuzzy vector according to the current comparison result vector and the fuzzy diagnosis matrix; The fault cause fuzzy vector is used to determine the fault type.

6. The water quality monitoring instrument fault diagnosis method according to claim 5, characterized in that: Using the fault cause fuzzy vector to determine the fault type includes: Selecting the maximum value in the fault cause fuzzy vector; The fault cause corresponding to the maximum value is determined as the fault cause of the water quality monitoring instrument.

7. The water quality monitoring instrument fault diagnosis method according to claim 1, characterized in that: Obtain the actual waveform data corresponding to various monitoring parameters of water quality monitoring instruments, including: Obtaining original waveform data corresponding to various monitoring parameters of the water quality monitoring instrument; The original waveform data are filtered to obtain actual waveform data.

8. A water quality monitoring instrument fault diagnosis device, characterized in that: include: The actual waveform data acquisition module is used to obtain the actual waveform data corresponding to various monitoring parameters of the water quality monitoring instrument; A standard waveform data acquisition module is used to acquire the standard waveform data corresponding to each actual waveform data; A comparison result obtaining module is used to compare each actual waveform data with the corresponding standard waveform data to obtain a comparison result; A fault diagnosis module is used to perform fault diagnosis on the water quality monitoring instrument according to the comparison result.

9. A water quality monitoring instrument fault diagnosis device, characterized in that: include: Memory for storing computer programs; A processor, used to implement the steps of the water quality monitoring instrument fault diagnosis method as described in any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the water quality monitoring instrument fault diagnosis method according to any one of claims 1 to 7 are implemented.

Images