Method, device and equipment for identifying abnormal state of environmental monitoring instrument and medium

Abstract

The invention discloses an abnormal state recognition method, device and equipment for an environmental monitoring instrument and a medium, and relates to the field of automatic online monitoring, and the method comprises the steps: collecting parameter signal values monitored by the environmental monitoring instrument in a sample testing process; drawing a curve based on the parameter signal values corresponding to the key parameters to obtain a current signal value change curve; performing consistency evaluation on corresponding segments in the current signal value change curve and the standard signal value change curve to obtain a consistency index; taking the index weight as a power exponent, performing weighted geometric average calculation on the consistency index to obtain geometric average credibility, and generating a dynamic penalty factor based on an index threshold and the consistency index; and calculating the product of the dynamic penalty factor and the geometric average credibility to obtain a credibility score, and judging whether the instrument is in an abnormal state or not based on the size relationship between the credibility score and a credibility threshold value. The accuracy of abnormal state recognition of the environment monitoring instrument can be improved, and the missing report rate and the false report rate are reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of automatic online monitoring, in particular to an environmental monitoring instrument abnormal state identification method, device, equipment and medium. BACKGROUND

[0002] In the field of environmental monitoring, automatic monitoring instruments (such as particulate matter sensors, water quality multi-parameter analyzers, gas analyzers, noise monitoring instruments, etc.) are deployed on various complex sites on a large scale to continuously and real-time collect environmental data. These instruments are the key infrastructure for realizing accurate environmental monitoring, early warning and scientific decision-making. However, in the actual operation process, due to factors such as harsh deployment environment, long-term continuous operation, and lack of manual daily on-site duty, it is difficult to avoid abnormal conditions of the monitoring instruments.

[0003] In order to identify the abnormal state of the monitoring instrument, the traditional method mainly relies on periodic manual on-site inspection, manual checking of instrument panel data or simple threshold alarm, which has the following disadvantages: poor timeliness: there is a significant delay from the occurrence of the abnormal state to the discovery, the manual inspection period is long, and the demand for rapid response to environmental events cannot be met, which may lead to missing or false reporting of key pollution events; strong concealment: many internal faults (such as slight aging of components and existence of parameter deviation) do not immediately lead to complete data failure at the initial stage, but only show accuracy decline or abnormal data in a specific range, and the abnormal mode is extremely concealed, lacking effective means to automatically identify such "sub-health" or "working with illness" state; strong professional dependence: the abnormal judgment is severely dependent on the experience and professional knowledge of the operation and maintenance personnel, and it is difficult to realize automatic diagnosis on a large scale (massive sites), and frequent inspection and troubleshooting with a large number of manpower will increase the operation and maintenance cost, and the accessibility is poor in remote and dangerous areas; narrow recognition range: the traditional threshold alarm method can only identify extreme abnormal values (such as out-of-range, signal loss, liquid shortage, etc.), and lacks comprehensive judgment ability for progressive degradation of sensor performance, complex internal faults (such as circuit abnormalities, logic errors), and abnormal conditions under specific working conditions (such as abnormal air pressure leading to slow response of the sensor). SUMMARY

[0004] Therefore, the purpose of the present application is to provide an environmental monitoring instrument abnormal state identification method, device, equipment and medium, which can improve the accuracy of environmental monitoring instrument abnormal state identification, reduce the false negative rate and false positive rate, and save the labor cost and time cost. The specific scheme is as follows:

[0005] In a first aspect, the present application discloses an environmental monitoring instrument abnormal state identification method, comprising:

[0006] Signal values of each key parameter at different time points are collected by an environmental monitoring instrument during sample testing, to obtain a plurality of parameter signal values corresponding to each key parameter; the key parameters include test environment parameters and instrument operation parameters;

[0007] A curve changing with time is drawn based on the plurality of parameter signal values corresponding to each key parameter respectively, to obtain a current signal value change curve;

[0008] Consistency evaluation is respectively performed on corresponding segments in the current signal value change curve and the standard signal value change curve, to obtain a consistency index corresponding to each segment; the standard signal value change curve is a curve changing with time drawn based on standard signal values corresponding to each key parameter;

[0009] An index weight corresponding to each segment is taken as an exponential index to perform weighted geometric mean calculation on the corresponding consistency index, to obtain a geometric mean credibility corresponding to each segment, and a dynamic penalty factor is generated based on a preset index threshold corresponding to each segment and the consistency index;

[0010] A product of the dynamic penalty factor and the geometric mean credibility of the corresponding segment is calculated to generate a data credibility score of the corresponding segment, and whether the environmental monitoring instrument is in an abnormal state is determined based on a size relationship between a plurality of data credibility scores corresponding to each key parameter and a credibility threshold.

[0011] Optionally, the consistency evaluation respectively performed on the corresponding segments in the current signal value change curve and the standard signal value change curve to obtain a consistency index corresponding to each segment comprises:

[0012] A similarity between the current signal value change curve and the standard signal value change curve is calculated to obtain a curve similarity value, and whether the curve similarity value is greater than or equal to a preset similarity threshold is determined;

[0013] If the curve similarity values corresponding to each key parameter are all greater than or equal to the preset similarity threshold, then the consistency evaluation is respectively performed on the corresponding segments in the current signal value change curve and the standard signal value change curve to obtain a consistency index corresponding to each segment.

[0014] Optionally, a generation formula of the dynamic penalty factor is:

[0015] ;

[0016] In the formula, i represents a key parameter, n represents a total number of key parameters, and m represents a total number of segments in the current signal value change curve and the standard signal value change curve. The consistency index of any segment corresponding to the i-th key parameter, Presents preset exponential threshold value of any segment corresponding to the i th key parameter, P is preset penalty intensity coefficient, and PF indicates the dynamic penalty factor.

[0017] Optionally, if the key parameter is temperature, the consistency of the respective segments in the current signal value change curve and the standard signal value change curve is evaluated to obtain a consistency index corresponding to each segment, including:

[0018] According to the preset segment mark, the initial segment, the rising segment, the stable segment and the falling segment in the current signal value change curve and the standard signal value change curve are sequentially evaluated for consistency to obtain a consistency index corresponding to each segment.

[0019] Optionally, the rising segment / falling segment in the current signal value change curve and the standard signal value change curve is evaluated for consistency to obtain a consistency index corresponding to the rising segment / falling segment, including:

[0020] The slope of the rising segment / falling segment in the current signal value change curve and the standard signal value change curve is fitted by the least square method to obtain a first slope and a second slope;

[0021] The ratio of the first slope to the second slope is calculated to obtain a slope ratio, and the absolute error of the slope ratio and 1 is calculated;

[0022] The mapping relationship between the preset absolute error value and the consistency index value is determined to determine the consistency index corresponding to the absolute error.

[0023] Optionally, the size relationship between the plurality of data credibility scores corresponding to each key parameter and the credibility threshold is determined to determine whether the environmental monitoring instrument is in an abnormal state, including:

[0024] It is determined whether the plurality of data credibility scores corresponding to each key parameter are all greater than the credibility threshold;

[0025] If there is a score less than the credibility threshold in the plurality of data credibility scores corresponding to the key parameter, it is determined that the environmental monitoring instrument is in an abnormal state;

[0026] If the plurality of data credibility scores corresponding to each key parameter are all greater than the credibility threshold, it is determined that the environmental monitoring instrument is in a normal state.

[0027] Optionally, the environmental monitoring instrument abnormal state recognition method further comprises:

[0028] All target credibility scores not greater than the credibility threshold in the data credibility scores corresponding to each key parameter are determined.

[0029] generate an early warning suggestion that the environmental monitoring instrument is in an abnormal state based on the target credibility score and the corresponding key parameters and segments, and send the early warning suggestion to a corresponding user terminal.

[0030] In a second aspect, the present application discloses an environmental monitoring instrument abnormal state recognition device, comprising:

[0031] The acquisition module is configured to acquire signal values of each key parameter at different time points monitored by the environmental monitoring instrument during sample testing, to obtain a plurality of parameter signal values corresponding to each key parameter; the key parameters include testing environment parameters and instrument operation parameters.

[0032] The curve drawing module is configured to draw a curve changing with time based on the plurality of parameter signal values corresponding to each key parameter, to obtain a current signal value change curve.

[0033] The evaluation module is configured to evaluate the consistency of the corresponding segments in the current signal value change curve and the standard signal value change curve respectively, to obtain a consistency index corresponding to each segment; the standard signal value change curve is a curve changing with time drawn based on standard signal values corresponding to each key parameter.

[0034] The first calculation module is configured to take the index weight corresponding to each segment as an exponential index, to perform weighted geometric mean calculation on the corresponding consistency index, to obtain a geometric mean credibility corresponding to each segment, and to generate a dynamic penalty factor based on a preset index threshold value corresponding to each segment and the consistency index.

[0035] The second calculation module is configured to calculate the product of the dynamic penalty factor and the geometric mean credibility of the corresponding segment, to generate a data credibility score of the corresponding segment.

[0036] The abnormal state determination module is configured to determine whether the environmental monitoring instrument is in an abnormal state based on the size relationship between the plurality of data credibility scores corresponding to each key parameter and a credibility threshold value.

[0037] In a third aspect, the present application discloses an electronic device comprising a processor and a memory; wherein the processor implements the aforementioned environmental monitoring instrument abnormal state recognition method when executing the computer program saved in the memory.

[0038] In a fourth aspect, the present application discloses a computer readable storage medium for storing a computer program; wherein the computer program is executed by a processor to implement the aforementioned environmental monitoring instrument abnormal state recognition method.

[0039] As can be seen, this application first collects the signal values ​​of each key parameter monitored by the environmental monitoring instrument at different times during sample testing, obtaining multiple parameter signal values ​​corresponding to each key parameter; the key parameters include test environment parameters and instrument operating parameters; curves of change over time are plotted based on the multiple parameter signal values ​​corresponding to each key parameter to obtain the current signal value change curve; consistency evaluation is performed on the corresponding segments of the current signal value change curve and the standard signal value change curve to obtain the consistency index corresponding to each segment; the standard signal value change curve is a curve of change over time plotted based on the standard signal values ​​corresponding to each key parameter; the index weight corresponding to each segment is used as a power exponent, and a weighted geometric mean is calculated on the corresponding consistency index to obtain the geometric mean confidence level corresponding to each segment, and a dynamic penalty factor is generated based on the preset index threshold corresponding to each segment and the consistency index; the product of the dynamic penalty factor and the geometric mean confidence level of the corresponding segment is calculated to generate the data confidence score of the corresponding segment, and the relationship between the multiple data confidence scores corresponding to each key parameter and the confidence threshold is used to determine whether the environmental monitoring instrument is in an abnormal state. This application first assesses the consistency between the current signal value change curve of the environmental monitoring instrument and corresponding segments of the standard signal value change curve, obtaining a consistency index for each segment. By comparing the change curves of key parameters in the current testing process with the standard curve, the reliability of the test data currently monitored by the environmental monitoring instrument can be ensured. Furthermore, compared to the overall consistency assessment, the segmented approach further improves the accuracy of the assessment. Next, the index weights corresponding to each segment are used as power exponents, and a weighted geometric mean is calculated for the corresponding consistency indices to obtain the geometric mean confidence level for each segment. This confidence level is then based on a preset index threshold for each segment. The consistency index generates a dynamic penalty factor. Finally, the product of the dynamic penalty factor and the geometric mean confidence level of the corresponding segment is calculated to generate the data confidence score of the corresponding segment. Based on the data confidence score, it is determined whether the instrument is in an abnormal state. By calculating the weighted geometric mean of the consistency index, a slight decrease in the consistency index can cause an exponential decay in the geometric mean confidence level. This makes the final calculated data confidence score more accurately reflect the confidence level of each segment, thereby improving the accuracy of instrument abnormal state identification and reducing the false alarm rate and missed alarm rate. In addition, the above method realizes automated abnormal state identification, thereby saving labor and time costs. Attached Figure Description

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the accompanying drawings needed to be used in the embodiments or prior art description will be briefly introduced. Obviously, the accompanying drawings in the following description only constitute a part of the embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of the provided drawings.

[0041] Figure 1 A flow chart of an abnormal state recognition method of an environmental monitoring instrument disclosed in the present application;

[0042] Figure 2 A schematic diagram of temperature change in a specific sample test process disclosed in the present application;

[0043] Figure 3 A flow chart of an abnormal state recognition method of an environmental monitoring instrument disclosed in the present application;

[0044] Figure 4 A structural schematic diagram of an abnormal state recognition device of an environmental monitoring instrument disclosed in the present application;

[0045] Figure 5 A structural diagram of an electronic device disclosed in the present application. DETAILED DESCRIPTION

[0046] The technical solutions in the embodiments of the present application will be described clearly and completely in the following with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments only constitute a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0047] The embodiments of the present application disclose an abnormal state recognition method of an environmental monitoring instrument, referring to Figure 1 The method comprises the following steps:

[0048] Step S11: collecting signal values of each key parameter of an environmental monitoring instrument at different time points during a sample test process, to obtain a plurality of parameter signal values corresponding to each key parameter; the key parameters include test environment parameters and instrument operation parameters.

[0049] It can be understood that the environmental monitoring instrument is the core equipment for obtaining environmental quality data, and its continuous operation and data quality directly affect the scientificity of environmental management decision. Moreover, the environmental monitoring instrument relies on various physical / chemical sensors (such as optical, electrochemical, catalytic combustion, electrode method, etc.), and these sensors have inherent characteristics: such as zero drift, range drift, sensitivity attenuation, response time variation, nonlinear error, etc., and are easily affected by environmental factors (temperature and humidity, air pressure, cross interference of pollutants), so in order to identify the abnormal state of the environmental monitoring instrument, the signal values of the key parameters including test environment parameters (such as environmental temperature, light intensity, humidity, air pressure, etc.) and instrument operation parameters (such as pump pressure, light source intensity, internal temperature, power voltage) need to be collected.

[0050] In the embodiment, in the process of testing samples (such as particulate matter samples, water quality samples, gas samples, etc.) by the environmental monitoring instrument (such as particulate matter sensors, water quality multi-parameter analyzers, gas analyzers, noise monitoring instruments, etc.), the signal values (such as temperature, light intensity, potential, measurement signal, etc.) of the key parameters at different times in the whole test process are collected in real time. For non-core test processes / non-key parameters, a larger error allowable range can be set.

[0051] Step S12: a curve changing with time is drawn based on the plurality of parameter signal values corresponding to each of the key parameters respectively, to obtain a current signal value change curve.

[0052] In the embodiment, after the plurality of parameter signal values corresponding to different key parameters in the test process of the environmental monitoring instrument are collected, further, a curve changing with time is drawn with the plurality of parameter signal values of each key parameter at different times as the ordinate and time (t) as the abscissa, to obtain a current signal value change curve corresponding to each key parameter.

[0053] Step S13: the consistency of the corresponding segments in the current signal value change curve and the standard signal value change curve is evaluated respectively, to obtain a consistency index corresponding to each segment; the standard signal value change curve is a curve changing with time drawn based on the standard signal values corresponding to each of the key parameters.

[0054] In the embodiment, after the current signal value change curve corresponding to each key parameter is drawn, the current signal value change curve can be compared with the corresponding segments in the standard signal value change curve changing with time drawn based on the standard signal values in advance according to a preset segmentation rule, to obtain a consistency index corresponding to each segment. By evaluating the consistency of the two curves, the reliability of the current test data (i.e. signal value) can be ensured.

[0055] The number of segments for each curve can be selected according to actual application needs and is related to the distribution characteristics of each key parameter during the test. The actual number of segments of the curve can be specifically selected based on different test indicators and test requirements.

[0056] In one specific implementation, the step of performing consistency evaluation on corresponding segments of the current signal value change curve and the standard signal value change curve to obtain a consistency index corresponding to each segment may specifically include: calculating the similarity between the current signal value change curve and the standard signal value change curve to obtain a curve similarity value, and determining whether the curve similarity value is greater than or equal to a preset similarity threshold; if the curve similarity values ​​corresponding to each of the key parameters are all greater than or equal to the preset similarity threshold, then performing consistency evaluation on corresponding segments of the current signal value change curve and the standard signal value change curve to obtain a consistency index corresponding to each segment. In this embodiment, see... Figure 2 As shown, Figure 2 The curves showing the change of the current signal value and the standard signal value corresponding to the temperature parameter are displayed. First, a similarity fitting is performed on the two curves to obtain the curve similarity value. The specific calculation formula is as follows:

[0057] ;

[0058] In the formula, This represents the i-th signal value in the curve representing the current signal value change of a key parameter (such as temperature). This represents the i-th signal value in the standard signal value change curve corresponding to a certain key parameter (such as temperature).

[0059] Next, determine the curve similarity value. Whether it is greater than or equal to the preset similarity threshold, if the curve similarity value of the key parameter is... If the similarity value is less than the preset similarity threshold, it indicates that the difference between the two curves corresponding to the key parameter (such as temperature) is large, suggesting that the test data (i.e., parameter signal values) is unreliable and may not reflect the true situation; if the curve similarity value of the key parameter is less than the preset similarity threshold, it indicates that the difference between the two curves is large, suggesting that the test data (i.e., parameter signal values) is unreliable and may not reflect the true situation; If the similarity threshold is greater than or equal to the preset threshold, it indicates that the difference between the two curves corresponding to the key parameter (such as temperature parameter) is small, and the test data (i.e. parameter signal value) is reliable. At this time, the subsequent process can continue, that is, to evaluate the consistency of each segment in the two curves separately, that is, to judge the consistency of the two curves segment by segment.

[0060] In a specific embodiment, if the key parameter is temperature, the consistency evaluation of the respective segments in the current signal value change curve and the standard signal value change curve respectively to obtain the consistency index corresponding to each segment can specifically include: in accordance with the preset segment markers, the initial segment, the rising segment, the stable segment and the falling segment in the current signal value change curve and the standard signal value change curve are sequentially evaluated for consistency to obtain the consistency index corresponding to each segment. In this embodiment, if the key parameter is temperature, the current signal value change curve and the standard signal value change curve can be divided according to the preset segment markers to obtain four different segments including the initial segment, the rising segment, the stable segment and the falling segment, which correspond to different stages of the entire test process respectively.

[0061] The calculation process of the consistency index of the initial segment (corresponding to the initial stage of the sample measurement process, which can reflect the test environment of the instrument and the standby state of the instrument, and the related parameter information (i.e. signal value) of this segment can reflect the stability of the test environment and the initial state of the instrument, etc.) includes the following steps: first, it is preliminarily determined whether each temperature value in the segment exceeds the upper limit of the temperature required by the test environment (such as the best test condition of the instrument is 40°C or less), if there is a temperature value exceeding 40°C in the segment, a temperature abnormality prompt information is generated or the linkage control system regulates the temperature in the station; if each temperature value in the segment does not exceed 40°C, the absolute error of the two temperature values at each time point in the two segment curves is calculated respectively , and the specific calculation formula is:

[0062] ;

[0063] In the formula, represents each temperature value in the initial segment of the current signal value change curve, represents each temperature value in the initial segment of the standard signal value change curve.

[0064] Next, according to the preset error threshold (such as = 10°C), the consistency ratio (indicating the percentage of temperature points with absolute error within the error threshold ) is calculated, and the specific calculation formula is:

[0065] ;

[0066] In the formula, is the total number of temperature points with absolute error within the error threshold , and M represents the total number of all temperature points in the initial segment.

[0067] Finally, the consistency ratio is determined based on the consistency index of the initial segment For example, when the consistency index of the initial segment is greater than or equal to a preset ratio threshold (e.g., 95%), it is considered that the signal values collected in the segment are consistent with the actual situation, and the consistency index of the initial segment is set to 1; for another example, when 90% ≤ the consistency index of the initial segment < 95%, it is considered that the signal values collected in the segment are consistent with the actual situation, and the consistency index of the initial segment is set to 0.9, and so on. If the consistency index of the initial segment is less than the preset ratio threshold (e.g., 50%), it is considered that the signal values collected in the segment are inconsistent with the actual situation, and the current abnormal state recognition process can be directly ended, and corresponding temperature abnormality alarm information can be generated.

[0068] The calculation process of the consistency index of the stationary segment includes the following steps: first, the absolute error of the two temperature values corresponding to the same time point in the segment is calculated, and the specific calculation formula is as follows: ;

[0069] In the formula, T represents the temperature value in the stationary segment of the current signal value change curve, and T' represents the temperature value in the stationary segment of the standard signal value change curve. Next, the average absolute error in the stationary segment is calculated, and the specific calculation formula is as follows:

[0070]

[0071] ;

[0072] In the formula, L represents the total number of temperature points in the stationary segment.

[0073] Finally, the consistency index of the stationary segment is determined according to the relationship between the average absolute error and a preset average error threshold (e.g., = 1°C), for example, when ≤ the average absolute error, it is considered that the segment is consistent with the actual situation, and the consistency index is = 1; for another example, when > the average absolute error, it is considered that the segment is consistent with the actual situation, and the consistency index is = 0.5.

[0074] ​​​​​​​​​​​​​​​​​​In this embodiment, a consistency evaluation is performed on the rising / falling segments of the current signal value change curve and the standard signal value change curve to obtain a consistency index corresponding to the rising / falling segments. Specifically, this may include: fitting the slopes of the rising / falling segments of the current signal value change curve and the standard signal value change curve using the least squares method to obtain a first slope and a second slope; calculating the ratio of the first slope to the second slope to obtain a slope ratio, and calculating the absolute error of the slope ratio with respect to 1; determining the consistency index corresponding to the absolute error based on a preset mapping relationship between the absolute error value and the consistency index value. In this embodiment, the same consistency index acquisition method is used for both the rising and falling segments. For example, for the rising segment, the slope of the rising segment of the current signal value change curve and the standard signal value change curve is first fitted using the least squares method to obtain a first slope. Second slope Among them, the first slope It can be obtained through the following formula:

[0075] ;

[0076] in, This represents the temperature values ​​within the rising segment of the current signal value change curve, when t=0. = ;

[0077] Second slope It can be obtained through the following formula:

[0078] ;

[0079] in, This represents the temperature values ​​within the rising segment of the standard signal value change curve, when t=0. = .

[0080] Next, calculate the first slope. With the second slope The ratio of the slope values ​​is obtained by the slope ratio. ,Right now And calculate the slope ratio The absolute error of 1 Then, based on the preset mapping relationship between the absolute error value and the consistency index value, the current absolute error is determined. The corresponding consistency index, for example, if the absolute error ≤ (like If the value is 0.1, then the segment is considered consistent with the actual situation, and the consistency index is 0.1. =1; For example, when ≤ ≤ (As =0.2), it is considered that the segment is consistent with the actual situation, and the consistency index is =0.8; and so on. Similarly, the consistency index of the descending segment can be determined by calculating the slope ratio.

[0081] Step S14: Taking the exponential weight of each segment as the power index, the corresponding consistency index is weighted and geometrically averaged to obtain the geometric mean credibility of each segment, and a dynamic penalty factor is generated based on the preset index threshold and the consistency index of each segment.

[0082] In this embodiment, after the consistency of the corresponding segments in the two signal value change curves corresponding to each key parameter is evaluated, the exponential weight of each segment is taken as the power index, and the corresponding consistency index is weighted and geometrically averaged to obtain the geometric mean credibility of each segment. The specific calculation formula is:

[0083] ;

[0084] By calculating the geometric mean credibility GMC, the nonlinear "short board effect" is introduced, which can make the final result highly dependent on the segment with the worst consistency. A slight numerical decline in the consistency index will cause exponential decay of GMC. Then, a dynamic penalty factor PF is generated based on the preset index threshold and the consistency index of each segment.

[0085] Specifically, the generation formula of the dynamic penalty factor is:

[0086] ;

[0087] In the formula, GMC represents the consistency index of any segment corresponding to the i-th key parameter, represents the preset index threshold of any segment corresponding to the i-th key parameter, P is a preset penalty intensity coefficient, and PF represents the dynamic penalty factor.

[0088] Step S15: The product of the dynamic penalty factor and the geometric mean credibility of the corresponding segment is calculated to generate the data credibility score of the corresponding segment, and based on the size relationship between the data credibility score corresponding to each key parameter and the credibility threshold, it is determined whether the environmental monitoring instrument is in an abnormal state.

[0089] ​​In this embodiment, the product of the dynamic penalty factor PF and the geometric mean credibility GMC of the corresponding segment is calculated, and the calculation result is taken as the data credibility score CCS of the corresponding segment (the score comprehensively reflects the data credibility corresponding to the corresponding key parameter, and the value range is [0, 1]), and the specific calculation formula is: Then, whether the plurality of data credibility scores corresponding to each key parameter is greater than the credibility threshold is respectively judged, if the data credibility scores corresponding to all key parameters are greater than the credibility threshold, it is determined that the environmental monitoring instrument is in a normal state; if there is a score in the plurality of data credibility scores corresponding to any one key parameter which is not greater than the credibility threshold, it is determined that the environmental monitoring instrument is in an abnormal state.

[0090] Specifically, the determination of whether the environmental monitoring instrument is in an abnormal state based on the size relationship between the plurality of data credibility scores corresponding to each key parameter and the credibility threshold can include: respectively judging whether the plurality of data credibility scores corresponding to each key parameter is greater than the credibility threshold; if there is a score in the plurality of data credibility scores corresponding to the key parameter which is less than the credibility threshold, it is determined that the environmental monitoring instrument is in an abnormal state; if the plurality of data credibility scores corresponding to each key parameter is greater than the credibility threshold, it is determined that the environmental monitoring instrument is in a normal state. That is, whether all data credibility scores corresponding to each key parameter is greater than the credibility threshold is respectively judged, if yes, it is determined that the environmental monitoring instrument is in a normal state, if no (i.e. there is a key parameter whose data credibility score is not greater than the credibility threshold), it is determined that the environmental monitoring instrument is in an abnormal state.

[0091] It can be seen that the embodiment of the application first evaluates the consistency of the current signal value change curve of the environmental monitoring instrument with the corresponding segment in the standard signal value change curve, obtains the consistency index corresponding to each segment, and through the consistency evaluation / comparison of the change curve of the key parameter in the current test process with the standard curve, the reliability of the test data monitored by the environmental monitoring instrument can be ensured, and compared with the overall consistency evaluation, the accuracy of the evaluation is further improved through the segmented manner; then, the index weight corresponding to each segment is taken as the power index, the corresponding consistency index is weighted and geometrically averaged, thereby obtaining the geometric mean credibility corresponding to each segment, and a dynamic penalty factor is generated based on the preset index threshold and the consistency index corresponding to each segment, and finally the product of the dynamic penalty factor and the geometric mean credibility of the corresponding segment is calculated, thereby generating the data credibility score of the corresponding segment, and based on the data credibility score, it is judged whether the instrument is in an abnormal state. Through the weighted geometric mean calculation of the consistency index, the exponential decay of the geometric mean credibility can be caused by the slight reduction of the consistency index, so that the finally calculated data credibility score can more accurately reflect the credibility of the segment data, thereby improving the accuracy of the instrument abnormal state recognition, reducing the false negative rate and the false positive rate, and through the above-mentioned manner, the automatic abnormal state recognition is realized, thereby saving the labor cost and the time cost. In addition, compared with the simple, static and single-point threshold judgment method of setting a fixed threshold (which cannot maintain the best judgment performance throughout the device life cycle, and may become too loose after the device ages, resulting in false negatives in the later stage of the device, or false positives in a specific scene, and the judgment accuracy decreases over time and with environmental changes), the application can realize dynamic abnormal state recognition in different scenes by generating a dynamic penalty factor, thereby fundamentally solving the problems of high false negatives, high false positives, difficult diagnosis and poor adaptability, and realizing more timely, accurate and reliable automatic evaluation of the abnormal state of the monitoring instrument itself.

[0092] The embodiment of the application discloses a specific environmental monitoring instrument abnormal state recognition method, as shown in Figure 3 The method comprises the following steps:

[0093] Step S21: acquiring the signal values of each key parameter at different times monitored by the environmental monitoring instrument during sample testing, to obtain a plurality of parameter signal values corresponding to each key parameter; the key parameters include test environment parameters and instrument operation parameters.

[0094] Step S22: respectively drawing curves changing with time based on the plurality of parameter signal values corresponding to each key parameter, to obtain a current signal value change curve.

[0095] Step S23: performing consistency evaluation on the corresponding segments in the current signal value change curve and the standard signal value change curve respectively to obtain a consistency index corresponding to each segment; the standard signal value change curve is a curve changing over time based on the standard signal values corresponding to each key parameter.

[0096] Step S24: taking the index weight corresponding to each segment as an exponential index to perform weighted geometric mean calculation on the corresponding consistency index to obtain a geometric mean credibility corresponding to each segment, and generating a dynamic penalty factor based on the preset index threshold corresponding to each segment and the consistency index.

[0097] Step S25: calculating the product of the dynamic penalty factor and the geometric mean credibility of the corresponding segment to generate a data credibility score of the corresponding segment, and determining whether the environmental monitoring instrument is in an abnormal state based on the size relationship between the data credibility scores corresponding to each key parameter and the credibility threshold.

[0098] Step S26: determining a target credibility score not greater than the credibility threshold among all the data credibility scores corresponding to each key parameter.

[0099] In the embodiment, if it is determined that the environmental monitoring instrument is in an abnormal state, the target credibility score not greater than the credibility threshold among all the data credibility scores CCS corresponding to each key parameter is taken as the cause of the abnormal state.

[0100] Step S27: generating an early warning suggestion that the environmental monitoring instrument is in an abnormal state based on the target credibility score and the corresponding key parameter and segment, and sending the early warning suggestion to the corresponding user terminal.

[0101] In the embodiment, after the cause of the abnormality is found, the corresponding early warning suggestion can be further generated based on the abnormal cause, for example, the early warning suggestion is generated based on the target credibility score causing the abnormality, the corresponding key parameter and the specific abnormal segment, and the early warning suggestion is sent to the corresponding user terminal, so that the corresponding technical personnel / operation personnel, etc. can quickly know that the current environmental monitoring instrument is in an abnormal state, and can accurately know the cause of the abnormal state, thereby quickly locating the abnormal cause to take corresponding measures to handle the abnormality.

[0102] Among them, the more specific processing process of the above steps S21 to S25 can refer to the corresponding content disclosed in the foregoing embodiments, which will not be repeated here.

[0103] It can be seen that when the environmental monitoring instrument is in an abnormal state, the embodiment of the present application generates a corresponding early warning suggestion based on the cause of the abnormal state, and sends the early warning suggestion to the corresponding user terminal. In this way, not only can the instrument in an abnormal state be found, but also the root cause of the abnormality can be quickly and accurately known, thereby providing decision support for rapid and accurate maintenance and improving the operation and maintenance efficiency. Moreover, compared with the traditional fault point positioning method of relying on personal experience to carry out a large number of on-site troubleshooting and testing after receiving an alarm, the present scheme directly provides an early warning suggestion containing an abnormal cause, thereby reducing the mean time to repair (MTTR, Mean time to repair) and operation and maintenance cost. In addition, by calculating the product of the dynamic penalty factor and the geometric mean confidence of the corresponding segment, and identifying the abnormal state based on the generated data confidence score, the gradual failure and performance degradation trend that cannot be found by the traditional threshold method can be identified in time, greatly reducing the false negative rate. Moreover, through multi-source information fusion and cross-validation (i.e., segment judgment of the parameter signal values of multiple key parameters), the real failure and environmental interference can be effectively distinguished, the alarm confidence is significantly improved, and the evaluation benchmark can be dynamically updated according to the change of the device (i.e., the environmental monitoring instrument) and the environment, thereby ensuring the effectiveness of the abnormal state identification in the whole life cycle. In addition, since no manual intervention is required, continuous monitoring and identification without manual attendance can be realized, the dependence on manpower is reduced, it is suitable for large-scale monitoring networks, and the long-term operation and maintenance cost is reduced.

[0104] Correspondingly, the embodiment of the present application also discloses an environmental monitoring instrument abnormal state identification device, as shown in Figure 4 The device comprises:

[0105] The collection module 11 is used for collecting signal values of each key parameter monitored by the environmental monitoring instrument during sample testing at different times, to obtain a plurality of parameter signal values corresponding to each key parameter; the key parameters include testing environment parameters and instrument operation parameters;

[0106] The curve drawing module 12 is used for drawing a curve changing with time based on the plurality of parameter signal values corresponding to each key parameter, to obtain a current signal value change curve;

[0107] The evaluation module 13 is used for respectively performing consistency evaluation on the corresponding segments in the current signal value change curve and the standard signal value change curve, to obtain a consistency index corresponding to each segment; the standard signal value change curve is a curve changing with time drawn based on the standard signal values corresponding to each key parameter;

[0108] The first calculation module 14 is configured to take the exponential weight corresponding to each segment as an exponent, weight the corresponding consistency index by geometric mean calculation, obtain the geometric mean credibility corresponding to each segment, and generate a dynamic penalty factor based on the preset index threshold corresponding to each segment and the consistency index.

[0109] The second calculation module 15 is configured to calculate the product of the dynamic penalty factor and the geometric mean credibility of the corresponding segment to generate the data credibility score of the corresponding segment.

[0110] The abnormal state determination module 16 is configured to determine whether the environmental monitoring instrument is in an abnormal state based on the size relationship between the data credibility scores corresponding to each key parameter and the credibility threshold.

[0111] The specific working procedures of each module described above can refer to the corresponding content disclosed in the foregoing embodiments, and will not be described here in detail.

[0112] Further, the embodiment of the present application further discloses an electronic device, Figure 5 The electronic device 20 shown in the figure is not considered as any limitation on the use range of the present application.

[0113] Figure 5 The electronic device 20 provided by the embodiment of the present application is shown in the structure diagram. The electronic device 20 specifically can include at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25 and a communication bus 26. The memory 22 is used to store a computer program, which is loaded and executed by the processor 21 to realize the related steps in the environmental monitoring instrument abnormal state recognition method disclosed in any of the foregoing embodiments. In addition, the electronic device 20 in the embodiment specifically can be an electronic computer.

[0114] In the embodiment, the power supply 23 is used to provide working voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and external devices, and the communication protocol followed by the communication interface 24 can be any communication protocol applicable to the technical solution of the present application, which will not be limited here; the input / output interface 25 is used to obtain external input data or output data to the outside, and the specific interface type can be selected according to the specific application needs, which will not be limited here.

[0115] In addition, the memory 22 as a carrier for resource storage can be a read-only memory, a random access memory, a magnetic disk or an optical disk, etc., and the resources stored thereon can include an operating system 221, a computer program 222, etc., and the storage mode can be temporary storage or permanent storage.

[0116] The operating system 221 is used to manage and control each hardware device on the electronic device 20 and the computer program 222, which can be Windows Server, Netware, Unix, Linux, etc. The computer program 222 can further include computer programs capable of completing other specific work in addition to the computer programs capable of completing the environmental monitoring instrument abnormal state identification method disclosed by any one of the preceding embodiments and executed by the electronic device 20.

[0117] Further, the present application also discloses a computer readable storage medium for storing a computer program; wherein the computer program is executed by a processor to implement the environmental monitoring instrument abnormal state identification method disclosed above. The specific steps of the method can refer to the corresponding content disclosed in the preceding embodiments, which will not be repeated here.

[0118] Further, the present application also discloses a computer program product comprising computer programs / instructions, which are executed by a processor to implement the steps of the environmental monitoring instrument abnormal state identification method disclosed above.

[0119] The embodiments in the specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts of each embodiment can be referred to each other. For the device disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple, and the related parts can refer to the method part.

[0120] The skilled person can further realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be realized by electronic hardware, computer software or a combination of both. In order to clearly show the interchangeability of hardware and software, the components and steps of each example have been described in the above description. Whether the functions are realized by hardware or software depends on the specific application and design constraints of the technical solution. The skilled person can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0121] The steps of the method or algorithm described in combination with the embodiments disclosed herein can be directly implemented by hardware, software modules executed by a processor, or a combination of both. The software modules can be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0122] Finally, it needs to be pointed out that in this article, the relationship terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between the entities or operations. Moreover, the terms "include", "contain" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method, article or equipment including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such process, method, article or equipment. Without more limitations, the element defined by the statement "including a" does not exclude the presence of other identical elements in the process, method, article or equipment including the element.

[0123] The above describes in detail the environmental monitoring instrument abnormal state identification method, device, equipment and medium provided by the present application. The principles and implementation modes of the present application are described by applying specific examples. The above example is only used to help understand the method and core idea of the present application. Meanwhile, for those skilled in the art, according to the idea of the present application, the specific implementation mode and application range will be changed. In summary, the content of the specification should not be understood as a limitation of the present application.

Claims

1. An environmental monitoring instrument abnormal state recognition method, characterized by, The method comprises the following steps: Collecting signal values of key parameters monitored by an environmental monitoring instrument during sample testing at different time points, to obtain a plurality of parameter signal values corresponding to each key parameter; the key parameters include test environment parameters and instrument operation parameters; Drawing a curve changing with time based on the plurality of parameter signal values corresponding to each key parameter, to obtain a current signal value change curve; Respectively evaluating the consistency of corresponding segments in the current signal value change curve and a standard signal value change curve, to obtain a consistency index corresponding to each segment; the standard signal value change curve is a curve changing with time drawn based on standard signal values corresponding to each key parameter; Taking the index weight corresponding to each segment as an exponential index to perform a weighted geometric mean calculation on the corresponding consistency index, to obtain a geometric mean credibility corresponding to each segment, and generating a dynamic penalty factor based on a preset index threshold value corresponding to each segment and the consistency index; Calculating the product of the dynamic penalty factor and the geometric mean credibility of the corresponding segment, to generate a data credibility score of the corresponding segment, and determining whether the environmental monitoring instrument is in an abnormal state based on the size relationship between the plurality of data credibility scores corresponding to each key parameter and a credibility threshold value.

2. The environmental monitoring instrument abnormal state recognition method according to claim 1, characterized in that, The step of respectively evaluating the consistency of corresponding segments in the current signal value change curve and the standard signal value change curve to obtain a consistency index corresponding to each segment comprises the following steps: Calculating the similarity between the current signal value change curve and the standard signal value change curve to obtain a curve similarity value, and determining whether the curve similarity value is greater than or equal to a preset similarity threshold value; If the curve similarity value corresponding to each key parameter is greater than or equal to the preset similarity threshold value, then respectively evaluating the consistency of corresponding segments in the current signal value change curve and the standard signal value change curve to obtain a consistency index corresponding to each segment.

3. The environmental monitoring instrument abnormal state recognition method according to claim 1, characterized in that, The generation formula of the dynamic penalty factor is: ； In the formula, denotes the consistency index of any segment corresponding to the i-th key parameter, denotes the preset index threshold of any segment corresponding to the i-th key parameter, P is a preset penalty intensity coefficient, and PF denotes the dynamic penalty factor.

4. The environmental monitoring instrument abnormal state recognition method of claim 1, wherein, If the key parameter is temperature, then the step of respectively evaluating the consistency of corresponding segments in the current signal value change curve and the standard signal value change curve to obtain a consistency index corresponding to each segment comprises the following steps: Respectively evaluating the consistency of an initial segment, an ascending segment, a stable segment and a descending segment in the current signal value change curve and the standard signal value change curve in sequence according to a preset segment marker, to obtain a consistency index corresponding to each segment.

5. The environmental monitoring instrument abnormal state recognition method according to claim 4, characterized in that, The step of evaluating the consistency of the ascending segment / descending segment in the current signal value change curve and the standard signal value change curve to obtain a consistency index corresponding to the ascending segment / descending segment comprises the following steps: Fitting the slope of the ascending segment / descending segment in the current signal value change curve and the standard signal value change curve by a least square method, to obtain a first slope and a second slope; Calculating the absolute error of the ratio of the first slope to the second slope; Determining the consistency index corresponding to the absolute error based on a mapping relationship between a preset absolute error value and a consistency index value.

6. The environmental monitoring instrument abnormal state recognition method of claim 1, wherein, The size relationship between the plurality of data credibility scores corresponding to each of the key parameters and the credibility threshold is used to determine whether the environmental monitoring instrument is in an abnormal state, including: Respectively determining whether the plurality of data credibility scores corresponding to each of the key parameters are all greater than the credibility threshold; If there is a score less than the credibility threshold in the plurality of data credibility scores corresponding to the key parameters, it is determined that the environmental monitoring instrument is in an abnormal state; If the plurality of data credibility scores corresponding to each of the key parameters are all greater than the credibility threshold, it is determined that the environmental monitoring instrument is in a normal state.

7. The environmental monitoring instrument abnormal state recognition method according to any one of claims 1 to 6, characterized in that, Further comprising: Determining a target credibility score that is not greater than the credibility threshold among all data credibility scores corresponding to each of the key parameters; Based on the target credibility score and the corresponding key parameters and segments, generating a warning suggestion that the environmental monitoring instrument is in an abnormal state, and sending the warning suggestion to the corresponding user terminal.

8. An environmental monitoring instrument abnormal state recognition apparatus characterized by comprising: Comprising: The acquisition module is used to acquire the signal values of each key parameter at different times monitored by the environmental monitoring instrument during sample testing, to obtain a plurality of parameter signal values corresponding to each of the key parameters; the key parameters include test environment parameters and instrument operation parameters; The curve drawing module is used to draw a curve changing with time based on the plurality of parameter signal values corresponding to each of the key parameters, to obtain a current signal value change curve; The evaluation module is used to evaluate the consistency of the corresponding segments in the current signal value change curve and the standard signal value change curve respectively, to obtain a consistency index corresponding to each segment; the standard signal value change curve is a curve changing with time based on the standard signal values corresponding to each of the key parameters; The first calculation module is used to take the index weight corresponding to each segment as an exponential index to weight the corresponding consistency index, to obtain a geometric mean credibility corresponding to each segment, and to generate a dynamic penalty factor based on the pre-set index threshold corresponding to each segment and the consistency index; The second calculation module is used to calculate the product of the dynamic penalty factor and the geometric mean credibility of the corresponding segment, to generate a data credibility score of the corresponding segment; The abnormal state determination module is used to determine whether the environmental monitoring instrument is in an abnormal state based on the size relationship between the plurality of data credibility scores corresponding to each of the key parameters and the credibility threshold.

9. An electronic device, comprising: Comprising a processor and a memory; wherein the processor implements the environmental monitoring instrument abnormal state recognition method of any one of claims 1 to 7 when executing the computer program saved in the memory.

10. A computer-readable storage medium, characterized in that, For storing a computer program; wherein the computer program is executed by a processor to implement the environmental monitoring instrument abnormal state recognition method of any one of claims 1 to 7.

Images