Geological disaster monitoring and early warning threshold adaptive generation device and method

Abstract

The invention provides a geological disaster monitoring early warning threshold adaptive generation method, which comprises the following steps of collecting historical acquisition data Xt-n... Xt-1 and Xt of observed quantity, and calculating an initial'early warning threshold 'th0 according to extreme value theorem fitting; when the latest collected data Xt + 1 of the observed quantity is reported, if the Xt + 1 is greater than the initial early warning threshold value th0, judging that the current state is an early warning state; if Xt + 1 is smaller than the initial early warning threshold value th0 but larger than the peak value pe, updating the initial early warning threshold value th0 to th1; and if Xt + 1 is smaller than the peak value pe, no special treatment is carried out. According to the method, through automatic updating of the early warning threshold, in the subsequent monitoring process of geological disasters, if the rule and the mode of the observed quantity are changed, the initially generated early warning threshold can be adaptively and dynamically updated, so that the effectiveness of the early warning threshold is effectively improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of instrument and meter maintenance, and particularly relates to a device and method for adaptively generating a geological disaster monitoring and early warning threshold. Background Art

[0002] There are many types of observed quantities in geological disaster monitoring, including but not limited to: surface displacement, soil moisture content, rainfall, deep displacement, infrasound, etc. Usually, after collecting and recording the collected data of these observed quantities, they will be compared with the "early warning threshold". If it exceeds the "early warning threshold", relevant personnel need to pay attention and conduct a risk investigation on the corresponding disaster point in a timely manner. Among them, most of this "early warning threshold" is set by relevant experts based on experience, which mainly has two drawbacks: First, the setting method of this "early warning threshold" is too subjective. If the setter has insufficient experience or the value is not accurate enough, it is easy to deviate too much; Second, even if the initial "early warning threshold" is set accurately, as time goes by, if the law and pattern of the observed quantity change, the initially set "early warning threshold" will no longer be applicable. Summary of the Invention

[0003] The purpose of the present invention is to overcome the deficiencies in the prior art and provide a device and method for adaptively generating a geological disaster monitoring and early warning threshold. The solution of the present invention can solve the problems existing in the above prior art.

[0004] The technical solution of the present invention:

[0005] According to a first aspect, there is provided a device for adaptively generating a geological disaster monitoring and early warning threshold, including a data acquisition unit, an initial early warning threshold calculation unit, a peak pe calculation unit, a comparison unit, and an updated early warning threshold calculation unit. The data acquisition unit sends the collected historical data to the initial early warning threshold calculation unit and the peak pe calculation unit, and sends the newly collected data X t+1 to the comparison unit. The peak pe calculation unit calculates the peak pe based on the historical data and sends the obtained peak pe to the initial early warning threshold calculation unit and the comparison unit. The initial early warning threshold calculation unit calculates the initial "early warning threshold" th0 based on the obtained data and sends it to the updated early warning threshold calculation unit and the comparison unit. The comparison unit compares the newly obtained data X t+1 , the initial "early warning threshold" th0, and the peak pe. If X t+1 is greater than the initial "early warning threshold" th0, it is determined that the current state is a warning state, and the updated early warning threshold calculation unit does not perform an update; if X t+1If it is less than the initial "warning threshold" th0 but greater than the peak value pe, the warning threshold calculation unit updates to calculate the new initial "warning threshold" th1; if X t+1 is less than the peak value pe, the warning threshold calculation unit does not perform an update.

[0006] Furthermore, the calculation formula for the peak value pe is: pe = max{X t-n ..X t-1 , X t}, where X t-n …X t-1 , X t is the historical acquisition data of the observed quantity.

[0007] Furthermore, the calculation formula for the "warning threshold" th0 is:

[0008] where pe is the peak value, q is a risk factor (generally between 10 -5 and 10 -3 ), N is the number of X exceeding the peak value pe, N total is the total number of all samples,

[0009] Furthermore, the calculation formula for the updated "warning threshold" th1 is:

[0010] Furthermore, the geological disaster monitoring and warning threshold adaptive generation device further includes a warning unit, and the warning unit issues a warning when the comparison unit determines that the current state is a warning state.

[0011] According to the second aspect, a geological disaster monitoring and warning threshold adaptive generation method is provided, including the following steps:

[0012] Collect the historical acquisition data X of the observed quantity t+1 …X t-1 , X t , and calculate an initial "warning threshold" th0 according to the extreme value theorem fitting;

[0013] When the latest acquisition data X of the observed quantity is reported, if X t+1 is greater than the initial "warning threshold" th0, it is determined that the current state is a warning state; if X t+1 is less than the initial "warning threshold" th0 but greater than the peak value pe, update the initial "warning threshold" th0 to th1; if X t+1 is less than the peak value pe, no special treatment is performed. t+1 is less than the peak value pe, no special treatment is performed.

[0014] Further, the calculation method of the peak pe is: pe = max{X t-n ..X t-1 ,X t}, where Xt-n…Xt-1, Xt are the historical acquisition data of the observed quantity.

[0015] Further, the calculation formula of the "early warning threshold" th0 is:

[0016] where pe is the peak value, q is the risk factor (generally between 10 -5 and 10 -3 ), N is the number of X exceeding the peak pe, N total is the total number of all samples,

[0017] Further, the calculation formula of the updated "early warning threshold" th1 is:

[0018] According to the third aspect, a geological disaster monitoring and early warning device is provided, and the geological disaster monitoring and early warning device includes a device for adaptively generating a geological disaster monitoring and early warning threshold according to the present invention.

[0019] Advantages of the present invention compared with the prior art:

[0020] 1) Through the automatic update of the early warning threshold, in the subsequent monitoring process of geological disasters, if the law and pattern of the observed quantity change, the initially generated "early warning threshold" can also be adaptively updated dynamically, thereby effectively improving its effectiveness;

[0021] 2) The early warning threshold of the present invention is calculated based on historical data and newly collected data, without any prior expert knowledge and manual setting rules, avoiding excessive deviation in threshold setting caused by being too subjective or lacking experience, and providing the accuracy of early warning. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The accompanying drawings included are used to provide a further understanding of the embodiments of the present invention, which form a part of the specification, are used to illustrate the embodiments of the present invention, and together with the written description are used to explain the principles of the present invention. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention, and for those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0023] Figure 1 Shows a schematic structural diagram of a device for adaptively generating a geological disaster monitoring and early warning threshold according to an embodiment of the present invention;

[0024] Figure 2 A schematic flowchart of a method for adaptively generating a geological disaster monitoring and early warning threshold according to an embodiment of the present invention is shown. Detailed implementation manners

[0025] It should be noted that, without conflict, the embodiments in the present application and the features in the embodiments may be combined with each other. The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. The following description of at least one exemplary embodiment is actually only illustrative and in no way limits the present invention and its application or use. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the scope of protection of the present invention.

[0026] It should be noted that the terms used herein are only for describing specific implementation manners and are not intended to limit the exemplary implementation manners according to the present application. As used herein, unless otherwise clearly specified in the context, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "include" and / or "comprise" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0027] Unless otherwise specifically stated, the relative arrangements of components and steps, numerical expressions, and numerical values set forth in these embodiments do not limit the scope of the present invention. At the same time, it should be understood that, for the convenience of description, the sizes of the various parts shown in the drawings are not drawn in actual proportional relationships. Technologies, methods, and devices known to those of ordinary skill in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and devices should be regarded as part of the authorization specification. In all the examples shown and discussed here, any specific value should be construed as merely exemplary and not as a limitation. Therefore, other examples of the exemplary embodiments may have different values. It should be noted that: like reference numerals and letters denote like items in the following drawings, and thus, once an item is defined in one drawing, it does not need to be further discussed in subsequent drawings.

[0028] As Figure 1 shown, according to the first aspect embodiment of the present invention, a device for adaptively generating a geological disaster monitoring and early warning threshold is provided, including a data acquisition unit, an initial early warning threshold calculation unit, a peak pe calculation unit, a comparison unit, and an updated early warning threshold calculation unit. The data acquisition unit sends the collected historical data to the initial early warning threshold calculation unit and the peak pe calculation unit, and sends the newly collected data X t+1Sent to the comparison unit, the peak pe calculation unit calculates the peak pe based on historical data and sends the obtained peak pe to the initial warning threshold calculation unit and the comparison unit. The initial warning threshold calculation unit calculates the initial "warning threshold" th0 based on the obtained data and sends it to the updated warning threshold calculation unit and the comparison unit. The comparison unit compares the newly obtained data X t+1 with the initial "warning threshold" th0 and the peak pe. If X t+1 is greater than the initial "warning threshold" th0, it is determined that the current state is a warning state, and the updated warning threshold calculation unit does not perform an update; if X t+1 is less than the initial "warning threshold" th0 but greater than the peak pe, the updated warning threshold calculation unit calculates the new initial "warning threshold" th1; if X t+1 is less than the peak pe, the updated warning threshold calculation unit does not perform an update.

[0029] Through the above device, the automatic update of the warning threshold enables the initial "warning threshold" to be adaptively and dynamically updated accordingly if the pattern and mode of the observed quantity change during the subsequent monitoring of geological disasters, thus effectively improving its effectiveness.

[0030] Furthermore, in one embodiment, the calculation formula for the peak pe is:

[0031] pe = max{X t-n ..X t-1 , X t}, where X t-n …X t-1 , X t are the historical acquisition data of the observed quantity.

[0032] Furthermore, in one embodiment, the calculation formula for the "warning threshold" th0 is:

[0033] where pe is the peak value, q is a risk factor (generally between 10 -5 and 10 -3 ), N is the number of X exceeding the peak pe, and N total is the total number of all samples.

[0034] Furthermore, in one embodiment, the calculation formula for the updated "warning threshold" th1 is: By automatically updating the warning threshold, no prior expert knowledge and manual setting rules are required, avoiding excessive deviation in threshold setting caused by being too subjective or lacking experience, and providing the accuracy of the warning.

[0035] Further, in one embodiment, a device for adaptively generating a geological disaster monitoring and early warning threshold further includes an early warning unit, which issues an early warning when the comparison unit determines that the current state is an early warning state.

[0036] According to an embodiment of the second aspect, a method for adaptively generating a geological disaster monitoring and early warning threshold is provided, including the following steps:

[0037] Collect the historical acquisition data X of the observed quantity t-n …X t-1 ,X t According to the extreme value theorem fitting, calculate an initial "early warning threshold" th0;

[0038] When the latest acquisition data X of the observed quantity t+1 is reported, if X t+1 is greater than the initial "early warning threshold" th0, it is determined that the current state is an early warning state; if X t+1 is less than the initial "early warning threshold" th0 but greater than the peak value pe, update the initial "early warning threshold" th0 to th1; if X t+1 is less than the peak value pe, no special treatment is performed.

[0039] Further, in one embodiment, the calculation method of the peak value pe is:

[0040] pe = max{X t-n ..X t-1 ,X t}, where Xt-n…Xt-1, Xt are the historical acquisition data of the observed quantity.

[0041] Further, in one embodiment, the calculation formula of the "early warning threshold" th0 is:

[0042] Among them, pe is the peak value, q is a risk factor (generally between 10 -5 and 10 -3 ), N is the number of X exceeding the peak value pe, N total is the total number of all samples,

[0043] Further, in one embodiment, the calculation formula of the updated "early warning threshold" th1 is:

[0044] According to the third aspect, a geological disaster monitoring and early warning device is provided, and the geological disaster monitoring and early warning device includes a device for adaptively generating a geological disaster monitoring and early warning threshold according to the present invention.

[0045] To further elaborate on a device and method for adaptively generating a geological disaster monitoring and early warning threshold according to the present invention, the present invention will be described in detail below with reference to the accompanying drawings.

[0046] 1) In the threshold generation section, it is necessary to collect the historical acquisition data X of the observed quantity t-n …X t-1 , X t , and then fit and calculate an initial "early warning threshold" th0 according to the extreme value theorem. According to the extreme value theorem, regardless of the distribution of X t-n ...X t-1 , X t , the extreme values (that is, the values exceeding the "early warning threshold") all follow the extreme value distribution, and its formula definition is as follows:

[0047]

[0048] Among them, according to different values of γ, there can be three tail shapes that match G γ (x): When γ > 0, G γ (x) follows the Frechet distribution; when γ = 0, G γ (x) follows the Gamma distribution; when γ < 0, G γ (x) follows the Uniform distribution. Schematic diagrams of the probability distribution functions of G γ (x) in the three cases are as shown in Figure 1 . Although using an unknown distribution as the input to train the EVD distribution can estimate the probability of potential extreme events, the number of extreme values is very scarce and it is difficult to intuitively define. Therefore, this patent is trained based on the content of the second extreme value theorem: regardless of the distribution of X t-n ...X t-1 , X t , the excess of the extreme value relative to a peak satisfies the Pareto distribution GPD (Generalized Pareto Distribution), and its probability distribution function is as shown in formula (2). Among them, pe is the peak value, and γ and σ are parameters to be estimated. Compared with the need for extreme value samples when fitting the EVD distribution, when fitting the GPD distribution, only the values X - pe exceeding the peak value pe need to be collected for training.

[0049]

[0050] In formula (2), the moment estimators MOE (Moment Estimators) can be used to estimate the parameters γ and σ. Specifically, the mean value of the extreme value distribution is replaced by , and the variance of the Pareto distribution is replaced by be replaced, where N is the number of X that exceeds the peak pe. Therefore, the parameters γ and σ of the Pareto distribution can be estimated by the moment method using formula (3). The initial warning threshold th0 can be calculated by formula (4), where pe is the peak, q is the risk factor (usually between 10 -5 and 10 -3 ), N is the number of X that exceeds the peak pe, and N total is the total number of all samples.

[0051]

[0052]

[0053] 2) In the threshold update section, due to the limitations of the data used for estimation and possible changes in the patterns and rules of the subsequent collected observation data, the initial warning threshold th0 may not always be effective. Therefore, a warning threshold update mechanism is designed in this patent: when the latest reported set of data exceeds the peak pe but does not exceed the warning threshold th n , we will update the warning threshold th n to th n+1 , and the update formula is as shown in (5):

[0054]

[0055] Advantages of the present invention compared with the prior art:

[0056] 1. Through the automatic update of the warning threshold, in the subsequent monitoring process of geological disasters, if the patterns and rules of the observation data change, the initially generated "warning threshold" can also be adaptively updated dynamically, thus effectively improving its effectiveness;

[0057] 2. The warning threshold of the present invention is calculated based on historical data and newly collected data, without any prior expert knowledge and manual setting rules, avoiding excessive deviation in threshold setting caused by being too subjective or lacking experience, and providing the accuracy of early warning.

[0058] The above are only the preferred embodiments of the present invention and are not used to limit the present invention. For those skilled in the art, the present invention can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A device for adaptively generating a monitoring and early warning threshold for geological disasters, characterized in that, It includes a data acquisition unit, an initial warning threshold calculation unit, a peak pe calculation unit, a comparison unit, and an updated warning threshold calculation unit. The data acquisition unit sends the collected historical data to the initial warning threshold calculation unit and the peak pe calculation unit, and sends the newly collected data X t+1 to the comparison unit. The peak pe calculation unit calculates the peak pe based on the historical data and sends the obtained peak pe to the initial warning threshold calculation unit and the comparison unit. The initial warning threshold calculation unit calculates the initial "warning threshold" th0 based on the obtained data and sends it to the updated warning threshold calculation unit and the comparison unit. The comparison unit compares the newly obtained data X t+1 , the initial "warning threshold" th0, and the peak pe. If X t+1 is greater than the initial "warning threshold" th0, it is determined that the current state is a warning state, and the updated warning threshold calculation unit does not perform an update; if X t+1 is less than the initial "warning threshold" th0 but greater than the peak pe, the updated warning threshold calculation unit calculates the new initial "warning threshold" th1; if X t+1 is less than the peak pe, the updated warning threshold calculation unit does not perform an update.

2. The geological disaster monitoring and early warning threshold adaptive generation device according to claim 1, characterized in that, The calculation method of the peak pe is as follows: pe = max{X t-n ...X t-1 , X t}, where Xt-n...Xt-1, Xt are the historical acquisition data of the observed quantity.

3. The geological disaster monitoring and early warning threshold adaptive generation device according to claim 2, wherein The calculation formula of the described "early warning threshold" th0 is as follows: Among them, pe is the peak value, q is the risk factor (generally between 10 -5 and 10 -3 ), N is the number of X exceeding the peak value pe, and N total is the total number of all samples, 4. A geological disaster monitoring and early warning threshold adaptive generation device according to claim 3, characterized in that The heating range of the temperature-limiting heating tube is: 80°C to 100°C.

5. An apparatus for adaptively generating a geological disaster monitoring and early warning threshold according to claim 4, the calculation formula for the updated "early warning threshold" th1 is as follows:

6. The geological disaster monitoring and early warning threshold adaptive generation device according to claim 5, characterized in that The described device for adaptively generating a geological disaster monitoring and early warning threshold further includes an early warning unit, and the early warning unit issues an early warning when the comparison unit determines that the current state is an early warning state.

7. A method for adaptively generating a geological disaster monitoring and early warning threshold using the geological disaster monitoring and early warning threshold adaptive generation device according to any one of claims 1 to 6, characterized in that, It includes the following steps: Collect historical acquisition data X of observed quantities t-n ...X t-1 ,X t , fit according to the extreme value theorem and calculate an initial "warning threshold" th0; When the latest collected data X of the observed quantity t+1 is reported, if X t+1 is greater than the initial "warning threshold" th0, then the current state is determined to be the warning state; if X t+1 is less than the initial "warning threshold" th0 but greater than the peak value pe, then update the initial "warning threshold" th0 to th1; if X t+1 is less than the peak value pe, then no special processing is performed.

8. A method for adaptively generating a geological disaster monitoring and early warning threshold according to claim 7, characterized in that The calculation method of the peak pe is as follows: pe = max{X t-n ... X t-1 , X t}, where Xt-n... Xt-1, Xt are the historical acquisition data of the observed quantity.

9. A method for adaptively generating a geological disaster monitoring and early warning threshold according to claim 7, characterized in that, The calculation formula of the described "warning threshold" th0 is as follows: Among them, pe is the peak value, q is the risk factor (generally between 10 -5 and 10 -3 ), N is the number of X exceeding the peak value pe, and N total is the total number of all samples, The calculation formula for the updated "warning threshold" th1 is as follows:

10. A geological disaster monitoring and early warning device, characterized in that, The described geological disaster monitoring and early warning device includes a device for adaptively generating a geological disaster monitoring and early warning threshold according to any one of claims 1-6.

Images