Photoelectric deflectometer alarm method and device based on feature extraction

Abstract

The invention discloses a photoelectric deflectometer alarm method based on feature extraction. The method comprises the following steps: acquiring bridge deflection data in real time through a photoelectric deflectometer; constructing a bridge deflection curve according to the bridge deflection data; according to the deflection curve, when the number of real-time detected deflection values is continuously larger than a preset event triggering deflection threshold value, and the preset number threshold value is met, the starting time of an event is recorded; when the number of deflection value connections detected in real time is lower than a preset event triggering threshold value and meets a preset number threshold value, recording the end time of the event; extracting characteristic values of data within the starting time and the ending time of the event; performing weighted calculation on the different characteristic values to obtain weighted characteristic values, and determining an influence degree numerical value of the change process of the bridge deflection on the bridge structure through the weighted characteristic values; and when the influence degree value is greater than a preset alarm threshold value, the photoelectric deflection meter gives an alarm. And the alarm accuracy of the photoelectric deflectometer is improved.

Description

Technical Field

[0001] The invention relates to the field of photoelectric detection equipment, and in particular to a photoelectric deflectometer alarm method and device based on feature extraction. Background Art

[0002] The photoelectric deflectometer is a high-precision measuring instrument, which is widely used in the fields of deformation monitoring of bridge engineering structures and deformation detection of mechanical equipment. However, in actual use, several fixed thresholds are usually set, and different levels of alarms are generated when the real-time detected deflection value exceeds different thresholds. For example: the first-level alarm threshold is set to 0.2mm, the second-level alarm level is 0.4mm, and the third-level alarm level is 0.6mm. When the real-time deflection value is greater than 0.2mm, a first-level alarm is generated, and so on. This method cannot truly reflect the real impact of the change in bridge deflection on the bridge structure, and will also produce a large number of false alarms, missed alarms and other problems. Summary of the invention

[0003] In order to solve at least one of the problems described in the above background technology, the present invention provides a photoelectric deflection instrument alarm method based on feature extraction, comprising:

[0004] Acquiring bridge deflection data in real time through a photoelectric deflectometer; constructing a bridge deflection curve based on the bridge deflection data;

[0005] According to the deflection curve, when the real-time detected deflection value is continuously greater than the number of preset event triggering deflection thresholds and meets the preset number threshold, the start time of the event is recorded; when the real-time detected deflection value is continuously lower than the number of preset event triggering thresholds and meets the preset number threshold, the end time of the event is recorded;

[0006] Extract feature values ​​from data within the start time and end time of the event;

[0007] Different eigenvalues ​​are weighted to obtain weighted eigenvalues, and the influence of the change process of bridge deflection on the bridge structure is determined by the weighted eigenvalues; when the influence value is greater than a preset alarm threshold, the photoelectric deflectometer alarms.

[0008] Optionally, before the step of obtaining the bridge deflection data in real time by using the photoelectric deflectometer, the method further includes:

[0009] Configure the system working parameters of the photoelectric deflectometer, configure the data receiving port parameters, configure the data preprocessing parameters, and configure the alarm parameters;

[0010] The photoelectric deflectometer application collects image information from the image sensor and calculates the bridge deflection data in real time through the position of the center of gravity of the target in the image;

[0011] The bridge deflection data is stored according to a preset data structure.

[0012] Optionally, the method further includes: preprocessing the deflection data, specifically including:

[0013] The deflection data is solved according to the bridge deflection data structure;

[0014] The calculated bridge deflection data is compensated, corrected and denoised.

[0015] Optionally, feature values ​​are extracted from data within the start time and end time of the event, and the feature values ​​include: maximum positive change, maximum negative change, mean value difference, event duration, mean square difference, and mean value difference before and after the event.

[0016] Maximum positive change = maximum positive value during the event period / sum of all positive values ​​during the event period;

[0017] Maximum negative change = maximum negative value during the event period / sum of all negative values ​​during the event period;

[0018] Mean difference = (mean value during the event - mean value before the event) / (mean value during the event + mean value before the event); Event duration = end time of the event - start time of the event; Mean square error difference = mean square error of the data during the event / mean square error of the data before the event;

[0019] The difference in means before and after an event = the mean before the event - the mean after the event.

[0020] Optionally, weighted calculation is performed on different eigenvalues ​​to obtain weighted eigenvalues, and the influence of the change process of the bridge deflection on the bridge structure is determined by the weighted eigenvalues, including:

[0021] The weight coefficient assigned to the maximum positive change is A, the weight coefficient assigned to the maximum negative change is B, the weight coefficient assigned to the difference in mean value is C, the weight coefficient assigned to the duration of the event is D, the weight coefficient assigned to the difference in mean square error is E, and the weight value assigned to the difference in mean before and after the event is F, where A+B+C+D+E+F=100;

[0022] The degree of influence of the change process of bridge deflection on the bridge structure is calculated by the following formula: influence value = A*maximum positive change + B*maximum negative change + C*difference in mean value + D*event duration + E*mean square difference + F*difference in mean before and after the event.

[0023] Optionally, also include:

[0024] When the impact value is less than the preset alarm threshold, the alarm information is discarded.

[0025] The present invention also provides a photoelectric deflectometer alarm device based on feature extraction, comprising:

[0026] A deflection curve construction module is used to obtain bridge deflection data in real time through a photoelectric deflectometer; and to construct a bridge deflection curve according to the bridge deflection data;

[0027] An event time recording module is used to record the start time of the event according to the deflection curve when the real-time detected deflection value is continuously greater than the preset event trigger deflection threshold value and meets the preset number threshold; when the real-time detected deflection value is continuously lower than the preset event trigger threshold value and meets the preset number threshold, record the end time of the event;

[0028] A feature value extraction module is used to extract feature values ​​from data within the start time and end time of an event;

[0029] The alarm data calculation module is used to perform weighted calculations on different eigenvalues ​​to obtain weighted eigenvalues, and determine the influence of the change process of bridge deflection on the bridge structure through the weighted eigenvalues; when the influence value is greater than a preset alarm threshold, the photoelectric deflectometer alarms.

[0030] Optionally, the method further includes: preprocessing the deflection data, specifically including:

[0031] A solution module, used for solving the deflection data according to the bridge deflection data structure;

[0032] The pre-processing module is used to compensate, correct and remove noise on the solved bridge deflection data.

[0033] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of any one of the methods described in the above claims when executing the computer program.

[0034] The present invention also provides a readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the method described in any one of the above claims are implemented.

[0035] The present invention provides a method and device for photoelectric deflectometer alarm based on feature extraction, which extracts features from the waveform when the bridge deflection changes, and evaluates the degree of influence of the change process of the bridge deflection on the bridge structure by weighting different features, thereby making the alarm more accurate and reducing the false alarms and missed alarms of the deflectometer. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 It is a flow chart of a photoelectric deflectometer alarm method based on feature extraction provided by an exemplary embodiment of the present invention;

[0037] Figure 2 It is an overall workflow diagram of a photoelectric deflectometer alarm method based on feature extraction provided by an exemplary embodiment of the present invention;

[0038] Figure 3 It is a structural schematic diagram of a photoelectric deflection instrument alarm detection device based on feature extraction provided by an exemplary embodiment of the present invention;

[0039] Figure 4 is a structural diagram of an electronic device provided by an exemplary embodiment of the present invention;

[0040] Figure 5 It is a collected signal provided by an exemplary embodiment of the present invention. DETAILED DESCRIPTION

[0041] Many specific details are set forth in the following description to facilitate a full understanding of the present invention. However, the present invention can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the connotation of the present invention, so the present invention is not limited to the specific implementation disclosed below.

[0042] Figure 1 The figure shows a flow chart of the photoelectric deflection instrument alarm method based on feature extraction provided by the present invention. Figure 1 As shown, the photoelectric deflection meter alarm method based on feature extraction includes:

[0043] Step S101, obtaining bridge deflection data in real time through a photoelectric deflectometer; and constructing a bridge deflection curve according to the bridge deflection data.

[0044] In the embodiment of the present invention, Figure 2 As shown, the working mode can be configured in advance, such as but not limited to: configuring system working parameters, configuring data receiving port parameters, configuring data preprocessing parameters, configuring alarm parameters, etc. Afterwards, the application collects image information from the image sensor, calculates the bridge deflection data in real time through the position of the center of gravity of the target in the image, and stores the deflection data according to the preset data structure. In this way, data support can be provided for subsequent data preprocessing.

[0045] Then, the deflection data is preprocessed, specifically including: settling the deflection data according to the deflection data structure; compensating for the missing data when there are omissions in the deflection data after solution; correcting the abnormal data when there are anomalies in the deflection data after solution; and denoising the noise data when there is noise in the deflection data after solution.

[0046] In the embodiment of the present invention, the deflection data is solved according to the data structure of the deflection data, and then the solved data is filtered, denoised, and abnormal data is eliminated. Methods such as smoothing filtering and eliminating extreme values ​​may be used.

[0047] Step S102, according to the deflection curve, when the real-time detected deflection value is continuously greater than the number of preset event trigger deflection thresholds and meets the preset number threshold, the start time of the event is recorded; when the real-time detected deflection value is continuously lower than the number of preset event trigger thresholds and meets the preset number threshold, the end time of the event is recorded.

[0048] The characteristic value extraction operation is performed on the deflection curve, including: performing preliminary event judgment on the deflection data, triggering the event when the number of real-time detected deflection values ​​continuously exceeding the preset event trigger deflection threshold meets the preset number threshold, and recording the start time of the event; when the number of real-time detected deflection values ​​continuously lower than the preset event trigger threshold meets the preset number threshold, it indicates that the event action is completed, and records the end time of the event.

[0049] Step S103, extracting feature values ​​from data within the start time and end time of the event.

[0050] Extract feature values ​​from data within the start and end time of the event. The feature values ​​include: maximum positive change, maximum negative change, mean value difference, event duration, mean square difference, and mean value difference before and after the event.

[0051] Maximum positive change = maximum positive value during the event period / sum of all positive values ​​during the event period;

[0052] Maximum negative change = maximum negative value during the event period / sum of all negative values ​​during the event period;

[0053] Mean difference = (mean value during the event - mean value before the event) / (mean value during the event + mean value before the event); Event duration = end time of the event - start time of the event; Mean square error difference = mean square error of the data during the event / mean square error of the data before the event;

[0054] The difference in means before and after an event = the mean before the event - the mean after the event.

[0055] Step S104, weighted calculation is performed on different eigenvalues ​​to obtain weighted eigenvalues, and the influence value of the change process of bridge deflection on the bridge structure is determined through the weighted eigenvalues; when the influence value is greater than a preset alarm threshold, the photoelectric deflectometer alarms.

[0056] The severity of the alarm is evaluated by weighting different features and the alarm information is uploaded, including:

[0057] The weight coefficient assigned to the maximum positive change is A, the weight coefficient assigned to the maximum negative change is B, the weight coefficient assigned to the difference in mean value is C, the weight coefficient assigned to the duration of the event is D, the weight coefficient assigned to the difference in mean square error is E, and the weight value assigned to the difference in mean before and after the event is F, where A+B+C+D+E+F=100;

[0058] The degree of influence of the change process of bridge deflection on the bridge structure is calculated by the following formula: influence value = A*maximum positive change + B*maximum negative change + C*difference in mean value + D*event duration + E*mean square difference + F*difference in mean before and after the event.

[0059] When the value of the influence degree is greater than the preset alarm threshold, the photoelectric deflectometer will alarm. When the value of the influence degree is less than the preset alarm threshold, the alarm information will be discarded.

[0060] In the embodiment of the present invention, Figure 2 As shown in the figure, by using a weighted method to evaluate the degree of harm of the alarm, the various characteristics of the entire process of the event are comprehensively considered to achieve a comprehensive evaluation of the impact of the event on the bridge structure. This can effectively improve the accuracy of the alarm and reduce the false alarms and missed alarms of the deflection meter.

[0061] For example: When there is a short-term obstruction between the photoelectric deflectometer and the target, such as birds flying over, it will cause the following Figure 5 The signal shown would generate a level 3 alarm (most serious) if the traditional alarm method is used, but the method of the present invention gives a very low comprehensive evaluation of the event.

[0062] Exemplary Devices

[0063] Figure 3 FIG. 1 is a schematic diagram of a photoelectric deflectometer alarm device based on feature extraction provided by an exemplary embodiment of the present invention. Figure 3 As shown, including:

[0064] A deflection curve construction module is used to obtain bridge deflection data in real time through a photoelectric deflectometer; and to construct a bridge deflection curve according to the bridge deflection data;

[0065] An event time recording module is used to record the start time of the event according to the deflection curve when the real-time detected deflection value is continuously greater than the preset event trigger deflection threshold value and meets the preset number threshold; when the real-time detected deflection value is continuously lower than the preset event trigger threshold value and meets the preset number threshold, record the end time of the event;

[0066] A feature value extraction module is used to extract feature values ​​from data within the start time and end time of an event;

[0067] The alarm data calculation module is used to perform weighted calculations on different eigenvalues ​​to obtain weighted eigenvalues, and determine the influence of the change process of bridge deflection on the bridge structure through the weighted eigenvalues; when the influence value is greater than a preset alarm threshold, the photoelectric deflectometer alarms.

[0068] Optionally, the method further includes: preprocessing the deflection data, specifically including:

[0069] A solution module, used for solving the deflection data according to the bridge deflection data structure;

[0070] The pre-processing module is used to compensate, correct and remove noise on the solved bridge deflection data.

[0071] Exemplary Electronic Devices

[0072] Figure 4 This is a structure of an electronic device provided by an exemplary embodiment of the present invention. Figure 4 As shown, the electronic device 40 includes one or more processors 41 and a memory 42 .

[0073] The processor 41 may be a central processing unit (CPU) or other forms of processing units having data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device to perform desired functions.

[0074] The memory 42 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory (cache), etc. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 41 may run the program instructions to implement the methods of the software programs of the various embodiments of the present invention described above and / or other desired functions. In one example, the electronic device may also include: an input device 43 and an output device 44, which are interconnected via a bus system and / or other forms of connection mechanisms (not shown).

[0075] In addition, the input device 43 may also include, for example, a keyboard, a mouse, etc.

[0076] The output device 44 can output various information to the outside, and can include, for example, a display, a speaker, a printer, a communication network and a remote output device connected thereto.

[0077] Of course, to simplify, Figure 4 Only some of the components related to the present invention in the electronic device are shown, and components such as a bus, an input / output interface, etc. are omitted. In addition, according to specific application conditions, the electronic device may also include any other appropriate components.

[0078] Exemplary computer program products and computer-readable storage media

[0079] In addition to the above-mentioned methods and devices, an embodiment of the present invention may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps of the method according to various embodiments of the present invention described in the above-mentioned "Exemplary Method" section of this specification.

[0080] The computer program product may be written in any combination of one or more programming languages ​​to write program code for performing the operations of the embodiments of the present invention, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0081] In addition, an embodiment of the present invention may also be a computer-readable storage medium having computer program instructions stored thereon, which, when executed by a processor, enable the processor to execute the steps of the method according to various embodiments of the present invention described in the above “Exemplary Method” section of this specification.

[0082] The computer readable storage medium can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, system or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0083] The basic principle of the present invention is described above in conjunction with specific embodiments. However, it should be pointed out that the advantages, strengths, effects, etc. mentioned in the present invention are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. must be possessed by each embodiment of the present invention. In addition, the specific details disclosed above are only for the purpose of illustration and facilitation of understanding, rather than limitation, and the above details do not limit the present invention to being implemented by adopting the above specific details.

[0084] Each embodiment in this specification 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 system embodiment, since it basically corresponds to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0085] The block diagrams of the devices, systems, equipment, and systems involved in the present invention are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagram. As will be appreciated by those skilled in the art, these devices, systems, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including", "comprising", "having", etc. are open words, referring to "including but not limited to", and can be used interchangeably with them. The words "or" and "and" used here refer to the words "and / or" and can be used interchangeably with them, unless the context clearly indicates otherwise. The word "such as" used here refers to the phrase "such as but not limited to", and can be used interchangeably with it.

[0086] The method and apparatus of the present invention may be implemented in many ways. For example, the method and apparatus of the present invention may be implemented by software, hardware, firmware, or any combination of software, hardware, firmware. The above order of steps for the method is only for illustration, and the steps of the method of the present invention are not limited to the order specifically described above, unless otherwise specifically stated. In addition, in some embodiments, the present invention may also be implemented as a program recorded in a recording medium, which includes machine-readable instructions for implementing the method according to the present invention. Thus, the present invention also covers a recording medium storing a program for executing the method according to the present invention.

[0087] It should also be noted that in the system, device and method of the present invention, each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent schemes of the present invention. The above description of the disclosed aspects is provided to enable any technician in the field to make or use the present invention. Various modifications to these aspects are very obvious to those skilled in the art, and the general principles defined here can be applied to other aspects without departing from the scope of the present invention. Therefore, the present invention is not intended to be limited to the aspects shown here, but in accordance with the widest range consistent with the principles and novel features disclosed here.

[0088] The above description has been given for the purpose of illustration and description. In addition, this description is not intended to limit the embodiments of the present invention to the forms disclosed herein. Although a number of example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions and sub-combinations thereof.

Claims

1. A photoelectric deflectometer alarm method based on feature extraction, characterized in that: include: Obtain bridge deflection data in real time through photoelectric deflectometer; constructing a bridge deflection curve according to the bridge deflection data; According to the deflection curve, when the real-time detected deflection value is continuously greater than the number of preset event triggering deflection thresholds and meets the preset number threshold, the start time of the event is recorded; When the number of real-time detected deflection values ​​connected is lower than the preset event trigger threshold and meets the preset number threshold, the end time of the event is recorded; Extract feature values ​​from data within the start time and end time of the event; Different eigenvalues ​​are weighted to obtain weighted eigenvalues, and the influence of the change process of bridge deflection on the bridge structure is determined by the weighted eigenvalues; when the influence value is greater than a preset alarm threshold, the photoelectric deflectometer alarms.

2. The method according to claim 1, characterized in that: Before the step of obtaining bridge deflection data in real time through the photoelectric deflectometer, it also includes: Configure the system working parameters of the photoelectric deflectometer, configure the data receiving port parameters, configure the data preprocessing parameters, and configure the alarm parameters; The photoelectric deflectometer application collects image information from the image sensor and calculates the bridge deflection data in real time through the position of the center of gravity of the target in the image; The bridge deflection data is stored according to a preset data structure.

3. The method according to claim 1 or 2, characterized in that: Also includes: Preprocess the deflection data, including: The deflection data is solved according to the bridge deflection data structure; The calculated bridge deflection data is compensated, corrected and denoised.

4. The method according to claim 1, characterized in that Extract characteristic values ​​from data within the start time and end time of the event, including: maximum positive change, maximum negative change, mean value difference, event duration, mean square difference, and mean value difference before and after the event; Maximum positive change = maximum positive value during the event period / sum of all positive values ​​during the event period; Maximum negative change = maximum negative value during the event period / sum of all negative values ​​during the event period; Mean difference = (mean value during the event - mean value before the event) / (mean value during the event + mean value before the event); Event duration = end time of the event - start time of the event; Mean square error difference = mean square error of the data during the event / mean square error of the data before the event; The difference in means before and after an event = the mean before the event - the mean after the event.

5. The method according to claim 1, characterized in that The weighted characteristic values ​​are calculated by weighting different characteristic values, and the influence of the change process of the bridge deflection on the bridge structure is determined by the weighted characteristic values, including: The weight coefficient assigned to the maximum positive change is A, the weight coefficient assigned to the maximum negative change is B, the weight coefficient assigned to the difference in mean value is C, the weight coefficient assigned to the duration of the event is D, the weight coefficient assigned to the difference in mean square error is E, and the weight value assigned to the difference in mean before and after the event is F, where A+B+C+D+E+F=100; The degree of influence of the change process of bridge deflection on the bridge structure is calculated by the following formula: influence value = A*maximum positive change + B*maximum negative change + C*difference in mean value + D*event duration + E*mean square difference + F*difference in mean before and after the event.

6. The method according to claim 1, characterized in that Also includes: When the impact value is less than the preset alarm threshold, the alarm information is discarded.

7. A photoelectric deflectometer alarm device based on feature extraction, characterized in that: include: Deflection curve building module, used to obtain bridge deflection data in real time through photoelectric deflectometer; constructing a bridge deflection curve according to the bridge deflection data; An event time recording module is used to record the start time of the event according to the deflection curve when the number of deflection values ​​detected in real time is continuously greater than the preset event triggering deflection threshold and meets the preset number threshold; When the number of real-time detected deflection values ​​connected is lower than the preset event trigger threshold and meets the preset number threshold, the end time of the event is recorded; A feature value extraction module is used to extract feature values ​​from data within the start time and end time of an event; The alarm data calculation module is used to perform weighted calculations on different eigenvalues ​​to obtain weighted eigenvalues, and determine the influence of the change process of bridge deflection on the bridge structure through the weighted eigenvalues; when the influence value is greater than a preset alarm threshold, the photoelectric deflectometer alarms.

8. The device according to claim 7, characterized in that Also includes: Preprocess the deflection data, including: A solution module, used for solving the deflection data according to the bridge deflection data structure; The pre-processing module is used to compensate, correct and remove noise on the solved bridge deflection data.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images