A leakage monitoring method and system for converter station valve halls based on photon counters

Abstract

The present invention relates to a method and system for monitoring water leakage in a converter station valve hall based on a photon counter. The method includes the following steps: arranging a line laser and a plurality of photon counters in the area to be detected for water leakage, and illuminating the area to be detected for water leakage in the converter station valve hall by the line laser; slicing the number of photons collected by the photon counters in the form of time series data to obtain time series data slices of the number of photons; respectively analyzing the time series data slices of the number of photons collected by each photon counter and obtaining the water leakage monitoring discrimination result of a single photon counter; and obtaining the water leakage monitoring discrimination result of the area to be detected for water leakage based on the water leakage monitoring discrimination result of a single photon counter. Compared with the prior art, the present invention has the advantages of expanding the dimension of monitoring data and improving the monitoring discrimination speed, etc.

Description

Technical Field

[0001] The present invention relates to the technical field of leakage monitoring, and in particular to a method and system for monitoring leakage in a converter station valve hall based on a photon counter. Background Art

[0002] The converter station valve hall is a key area in a high-voltage direct current (HVDC) system, bearing the important tasks of power conversion and regulation. As an important hub in the power system, the valve hall is responsible for converting alternating current power into direct current through a converter valve, or converting direct current back into alternating current power. The stability of its function is crucial for the safety and reliability of the power system. The valve hall is equipped with core facilities such as converter valves, DC electrical equipment, and control systems. These devices not only bear high voltage and large current loads but also need to work in extreme environments for a long time. Therefore, the operation status of the valve hall directly affects the overall efficiency of the converter station. If problems occur in the valve hall, a series of chain reactions may be triggered, even affecting the power transmission over a large area.

[0003] However, due to the long-term action of engineering stress and environmental factors in the converter station valve hall, its equipment and structure will gradually age and wear, especially the valve hall ceiling. As an important part of the valve hall, the ceiling bears great physical pressure and environmental changes and is easily affected by moisture, temperature changes, and air humidity. Long-term temperature differences may cause the sealing materials of the ceiling to age or be damaged, thus triggering leakage problems. In addition, during the operation of the equipment in the valve hall, facilities such as pipelines and ventilation systems may generate condensate water, and this moisture may also leak along the ceiling to the equipment area. Once the leakage is not discovered and dealt with in time, the moisture will accumulate near the equipment under the ceiling, affecting the normal operation of the equipment. Especially for high-voltage electrical equipment such as converter valves, once exposed to a humid environment, it may lead to a decline in equipment performance or a malfunction. Therefore, the existence of ceiling leakage problems may seriously threaten the safety of the equipment inside the valve hall and the overall stable operation of the converter station.

[0004] The converter valves, control systems, and related electrical equipment installed inside the valve hall are crucial facilities in the system, and they need to maintain a high degree of reliability and stability. In the event of water leakage in the valve hall, moisture may penetrate into the converter valves and other electrical equipment. In severe cases, it may lead to equipment failures, performance degradation, and even affect the overall operating efficiency and safety of the converter station. Especially in high-voltage DC systems, any equipment failure may cause instability in the power system, resulting in interrupted energy supply or equipment damage, causing significant economic losses and social impacts. Therefore, in order to ensure the normal operation of the equipment in the converter station valve hall, effective monitoring measures must be taken to detect and quickly respond to the occurrence of water leakage faults in the valve hall in real time. This can not only protect the equipment from water damage but also identify potential risks in advance, perform repairs in a timely manner, ensure the safety, reliability, and stability of the entire converter station system, and thus provide a strong guarantee for the stable operation of the power system.

[0005] CN117073910A discloses a leakage monitoring system for the roof of a converter station valve hall, which uses image recognition to monitor water leakage in the converter station valve hall. However, due to the high performance requirements of image processing for processing equipment, the processing speed is greatly affected by the performance of the processing equipment, and it is difficult to obtain monitoring results quickly. Moreover, the accuracy of the output results is affected by the training data set. When it is difficult to obtain sufficient training images, it is difficult to ensure the accuracy of the final results. Therefore, a leakage monitoring method that can ensure both monitoring accuracy and monitoring speed is needed. Summary of the Invention

[0006] The purpose of the present invention is to provide a method and system for monitoring water leakage in a converter station valve hall based on a photon counter. By collecting the number of photons in space through the photon counter and further processing the photon number time series data through slicing and feature calculation, water leakage monitoring in the converter station valve hall is realized.

[0007] The purpose of the present invention can be achieved through the following technical solutions:

[0008] A method for monitoring water leakage in a converter station valve hall based on a photon counter includes the following steps:

[0009] Set a line laser in the area to be detected for water leakage and illuminate the area to be detected for water leakage in the converter station valve hall through the line laser. Among them, the laser trajectory emitted by the set line laser is a fan-shaped column with a preset thickness, and the laser trajectory coverage area covers the area to be detected for water leakage;

[0010] Set multiple photon counters in the area to be detected for water leakage. Among them, the set photon counter measures the number of photons within a fixed wavelength range it receives, and the measurable wavelength range of the photon counter overlaps with the laser wavelength range emitted by the line laser;

[0011] Slice the number of photons collected by the photon counter in the form of time series data to obtain a time series data slice of the number of photons. The time series data slice of the number of photons includes a one-dimensional time series array with a preset length organized at a preset sampling rate, the start time of the time series data, and sampling rate information.

[0012] Analyze the time series data slices of the number of photons collected by each photon counter respectively and obtain the leakage monitoring discrimination result of a single photon counter.

[0013] Obtain the leakage monitoring discrimination result of the leakage area to be detected based on the leakage monitoring discrimination result of a single photon counter.

[0014] When the leakage area to be detected is a rectangular area, the setting of the line laser includes the following steps:

[0015] Determine the area to be detected and the position where the line laser can be installed: According to the on-site conditions, determine the horizontal boundary of the leakage area to be detected and the position range where the line laser can be installed. The position where the line laser can be installed is on the wall or frame of the building, represented as one or several line segments.

[0016] Determine the installation position of the line laser: Draw the perpendicular bisector of the short side of the rectangular leakage area to be detected, which forms an intersection with the line segment describing the position where the line laser can be installed, and use the intersection as the installation position of the line laser.

[0017] Determine the fan angle and effective distance of the line laser: The parameters of the line laser include the fan angle and the effective distance L , and the parameters of the line laser satisfy the following conditions: 1) The effective distance L exceeds the maximum value of the distances from the installation position of the line laser to all positions within the leakage area to be detected; 2) The laser fan angle satisfies that the effective working sector range of the line laser covers the rectangular leakage area to be detected, that is, , where b is the length of the short side of the rectangular leakage area to be detected, d is the distance between the installation position of the line laser and the short side of the rectangular leakage area to be detected;

[0018] Determine the installation angle of the line laser: Set the vertical installation angle of the line laser to be horizontal, that is, the plane of the fan-shaped column formed by the laser trajectory is parallel to the horizontal plane. At the same time, set the horizontal installation angle of the line laser to face the leakage area to be detected, that is, the angular bisector of the fan-shaped cross-section of the fan-shaped column formed by the laser trajectory coincides with the perpendicular bisector of the short side of the rectangular area to be detected.

[0019] The setting of the photon counter includes the following steps:

[0020] Determine the installable positions of the photon counters: According to the on-site conditions, determine the positions where the photon counters can be installed. The positions where the photon counters can be installed are on the walls or frameworks of the building, represented as one or several line segments, and are consistent with the horizontal positions of the installable line lasers;

[0021] Based on the installable positions of the photon counters, configure multiple photon counters in the horizontal direction. The receiving probe directions of all photon counters face the area to be detected for water leakage; in the vertical direction, set the height difference between the installation height of the photon counters and the line lasers to be greater than a preset threshold; set the installation angle attitude of the photon counters to be parallel to the horizontal plane.

[0022] The difference between the upper and lower limits of the laser wavelength emitted by the line laser does not exceed 50 nm.

[0023] The measurable wavelength range of the photon counters is less than or equal to the laser wavelength range emitted by the line lasers.

[0024] When performing time-series data slicing, make adjacent time-series data slices have partial overlapping data according to a preset overlapping rate.

[0025] Analyze the time-series data slices of the photon counts collected by each photon counter respectively and obtain the water leakage monitoring discrimination results of a single photon counter, which specifically include the following steps:

[0026] Set a set of multi-dimensional feature discrimination methods for one-dimensional time series. The set of multi-dimensional feature discrimination methods includes discrimination methods based on root mean square value, kurtosis index, EMD decomposition features, and synchrosqueezed wavelet transform time-frequency spectrum energy features of sensitive frequency bands;

[0027] Select multiple feature discrimination methods from the set of multi-dimensional feature discrimination methods, calculate the corresponding features respectively based on the selected feature discrimination methods, and determine whether a water leakage fault has occurred according to the calculated features respectively;

[0028] Summarize the discrimination results of multiple feature discrimination methods for a single photon counter, and judge whether the corresponding photon counter has detected a water leakage fault according to the weight summation rule.

[0029] The discrimination method based on the root mean square value includes the following steps:

[0030] Extract the root mean square value features based on the data of each photon count time series slice of a certain photon counter;

[0031] Set the root mean square value discrimination limit as the mean of the baseline data plus three times the standard deviation of the baseline data. The baseline data are multiple root mean square value features corresponding to multiple photon count time series slice data within a preset time;

[0032] Set the first discrimination time and the first discrimination count limit and discriminate the water leakage fault: within the set first discrimination time, determine the number of times that the root mean square value feature calculated based on multiple photon number time series slice data of the photon counter is greater than or equal to the root mean square value discrimination limit, denoted as the first count. If the first count is greater than or equal to the first discrimination count limit, it is determined that the photon counter has detected a water leakage fault;

[0033] The discrimination method based on the kurtosis index includes the following steps:

[0034] Extract the kurtosis index feature based on each photon number time series slice data of a certain photon counter;

[0035] Set the kurtosis index discrimination limit to three times the standard deviation of the baseline data mean floating upward of the baseline data. The baseline data is multiple kurtosis index features corresponding to multiple photon number time series slice data within a preset time;

[0036] Set the second discrimination time and the second discrimination count limit and discriminate the water leakage fault: within the set second discrimination time, determine the number of times that the kurtosis index feature calculated based on multiple photon number time series slice data of the photon counter is greater than or equal to the kurtosis index discrimination limit, denoted as the second count. If the second count is greater than or equal to the second discrimination count limit, it is determined that the photon counter has detected a water leakage fault;

[0037] The discrimination method based on the EMD decomposition characteristic includes the following steps:

[0038] Perform EMD decomposition processing on the photon number time series slice data x 1 ,x 2 ,…,x N to obtain the corresponding IMF components of each order( c 1 ( x ), c 2 ( x ),…, c m ( x )) T , where N represents the number of data in the slice, c i ( x ) represents the i -th order IMF component, m represents that the photon number time series slice data is divided into m IMF components;

[0039] Set the EMD decomposition discrimination index and the limit value of the EMD decomposition discrimination index: Take the data of the first-order IMF component after the EMD decomposition of the photon number time series slice data c 1 ( x ) and obtain the data of the first-order IMF component c 1 ( x ) and find the maximum value , the average value and the standard deviation . Take the maximum value of the data of the first-order IMF component of the photon number time series data c 1 ( x ) as the EMD decomposition discrimination index, and take the sum of the average value of the data of the first-order IMF component of the photon number time series data c 1 ( x ) and 3 times the standard deviation as the limit value of the EMD decomposition discrimination index , that is ; ;

[0040] Set the third discrimination time and the limit value of the third discrimination times and discriminate the water leakage fault: Within the set third discrimination time, judge the number of times that the EMD decomposition discrimination index calculated based on multiple photon number time series slice data of the photon counter is greater than or equal to the limit value of the EMD decomposition discrimination index . Denote it as the third number of times. If the third number of times is greater than or equal to the limit value of the third discrimination times, it is determined that the photon counter monitors a water leakage fault;

[0041] The discrimination method based on the time-frequency spectrum energy characteristics of the sensitive band synchrosqueezed wavelet transform includes the following steps:

[0042] Based on each photon number time series slice data of a certain photon counter, calculate its synchrosqueezed wavelet transform time-frequency spectrum characteristics represented by a two-dimensional matrix:

[0043] ,

[0044] where T and F respectively represent the maximum number of numbers in the time and frequency dimensions. The first dimension of the obtained synchrosqueezed wavelet transform time-frequency spectrum is time, and the second dimension is frequency;

[0045] Set the sensitive frequency band and complete the time-frequency spectrum interception: Set the lower limit and the upper limit ,and intercept the synchrosqueezing wavelet transform time-frequency spectrum feature matrix according to the sensitive frequency band ,that is, only retain the synchrosqueezing wavelet transform time-frequency spectrum within the sensitive frequency band;

[0046] Accumulate the intercepted synchrosqueezing wavelet transform time-frequency spectrum in the frequency dimension to obtain the sensitive frequency band energy time series data ,where ,obtain the maximum value in the sensitive frequency band energy time series data ,average value and standard deviation ,take the maximum value of the sensitive frequency band energy time series data as the energy feature discrimination index, and take the sum of the average value and 3 times the standard deviation as the limit value of the time-frequency energy feature discrimination index ,that is ;

[0047] Set the fourth discrimination time and the fourth discrimination number limit and discriminate the water leakage fault: within the set fourth discrimination time, judge the synchrosqueezing wavelet transform sensitive frequency band energy feature discrimination index calculated based on the multiple photon number time series slice data of this photon counter is greater than or equal to the limit value of the time-frequency energy feature discrimination index The number of times is recorded as the fourth number. If the fourth number is greater than or equal to the fourth discrimination number limit, it is determined that this photon counter monitors a water leakage fault;

[0048] Perform pseudo-color processing on the intercepted synchrosqueezing wavelet transform time-frequency spectrum and send it into a pre-trained convolutional neural network model for discrimination to obtain the water leakage monitoring discrimination result for a single photon number time series data slice;

[0049] Set the fifth discrimination time and the fifth discrimination number limit and discriminate the water leakage fault: within the set fifth discrimination time, judge the number of times that the output result of the neural network model calculated based on the multiple photon number time series slice data of this photon counter indicates a water leakage fault, which is recorded as the fifth number. If the fifth number is greater than or equal to the fifth discrimination number limit, it is determined that this photon counter monitors a water leakage fault.

[0050] Summarize the discrimination results of multiple feature discrimination methods for a single photon counter, and judge whether the corresponding photon counter monitors a water leakage fault according to the weighted summation rule, specifically:

[0051] For the multi-dimensional feature discrimination methods of multiple one-dimensional time series selected, set the weights of the discrimination results of different features ,and ensure that , P is the number of discrimination results obtained by using multiple feature discrimination methods;

[0052] For the discrimination result output by a certain feature discrimination method, if the result is a detected fault, the discrimination result is set to 1, and if the result is no fault, the result is set to 0. Based on the set weights and the discrimination results output by each feature discrimination method, a weighted sum is performed to obtain a summary discrimination result;

[0053] Set the limit value of the discrimination result for the leakage fault monitoring of a single photon counter. If the summary discrimination result is greater than the limit value of the discrimination result for the leakage fault monitoring of a single photon counter, it is considered that the leakage monitoring result of this photon counter is faulty.

[0054] A leakage monitoring system for the valve hall of a converter station based on a photon counter, used to implement the method described above. The system includes a line laser, multiple photon counters, a control unit, a data processing unit, a communication unit, and a human-machine interface. Among them,

[0055] The line laser is used to achieve non-stop scanning and irradiating the area to be detected for leakage;

[0056] The photon counter is used to collect the change in the number of photons in the area to be detected for leakage, and obtain the time series data of the number of photons;

[0057] The control unit is used to achieve the coordinated control of the line laser, photon counter, and data processing unit;

[0058] The data processing unit is used to slice and analyze the time series data of the number of photons collected by the photon counter, and output the leakage monitoring discrimination result;

[0059] The communication unit is used to achieve the communication inside the leakage monitoring system of the valve hall of the converter station and with the outside;

[0060] The human-machine interface is used to achieve the interaction between personnel and the leakage monitoring system of the valve hall of the converter station.

[0061] Compared with the prior art, the present invention has the following beneficial effects:

[0062] (1) The present invention proposes a leakage monitoring method for the valve hall of a converter station based on a line laser and a photon counter. Compared with the prior art, it innovatively uses a photon counter as the sensing unit, and the sensing dimension is expanded compared with the prior art, supplementing the existing data dimension. The technology of the present invention can make the data used for leakage monitoring more abundant and optimize the leakage monitoring effect of the valve hall of the converter station.

[0063] (2) The present invention collects one-dimensional photon number time series data through a photon counter, and uses simple numerical type features such as root mean square value, kurtosis index, and maximum value of the Imf component obtained by EMD decomposition as discrimination indicators, achieving a faster discrimination speed in data judgment compared with the existing technology.

[0064] (3) The present invention adopts the energy feature of the synchrosqueezed wavelet transform time-frequency spectrum as the judgment method for key features, enriching the application depth of the photon number time series data slices and further improving the accuracy of leakage monitoring.

[0065] (4) The present invention proposes a configuration method for a line laser and a photon counter in engineering, which fully considers engineering conditions and application effects compared with the existing technology and can guide the implementation of the technology of the present invention in engineering.

[0066] (5) The present invention can achieve effective leakage monitoring of the converter station valve hall without obtaining a large amount of original data, and has stronger practicability and practical application value compared with the existing technology.

[0067] (6) The data processing method of the present invention is simple, does not rely on the performance of computing devices, has low requirements for computing devices, and is easier to deploy in actual applications. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] Figure 1 is the flowchart of the method of the present invention;

[0069] Figure 2 is a top view schematic diagram of the leakage monitoring line laser and photon counter configuration scheme in the converter station valve hall in an embodiment;

[0070] Figure 3 is a side view schematic diagram of the leakage monitoring line laser and photon counter configuration scheme in the converter station valve hall in an embodiment;

[0071] Figure 4 is the flowchart of the leakage monitoring method for a single photon counter in an embodiment;

[0072] Figure 5 is a schematic diagram of the pre-trained convolutional neural network structure for processing the time-frequency spectrum of the sensitive frequency band of the photon number time series slices in an embodiment;

[0073] Figure 6 is the schematic diagram of the system structure of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0074] The present invention will be described in detail below with reference to the drawings and specific embodiments. This embodiment is implemented on the premise of the technical solution of the present invention, and gives the detailed implementation method and specific operation process, but the protection scope of the present invention is not limited to the following embodiments.

[0075] Embodiment 1

[0076] First, the present invention provides a method for monitoring water leakage in a converter station valve hall by combining a photon counter and a line laser. The line laser irradiates the area to be detected for water leakage in the space, and at the same time, a photon counter is used to capture photons in a specific frequency band in the space, and by analyzing the fluctuation change of the number of photons, it is judged whether there is a water leakage fault in the space, so as to realize the rapid identification and monitoring of the water leakage fault.

[0077] Specifically, as Figure 1 shown, it includes the following steps:

[0078] Step 1) Set a line laser in the area to be detected for water leakage and illuminate the area to be detected for water leakage in the converter station valve hall through the line laser.

[0079] In this embodiment, the set line laser has a certain fan angle and effective distance, and the laser trajectory emitted by it is a fan-shaped column with a certain thickness. It is necessary to ensure that the laser trajectory emitted by the line laser covers the area to be detected for water leakage. The laser wavelength emitted by the set line laser is distributed in a relatively narrow range. Preferably, the difference between the upper and lower limits of the laser wavelength emitted by the set line laser does not exceed 50 nm.

[0080] Step 2) Set multiple photon counters in the area to be detected for water leakage.

[0081] The set photon counter can measure the number of photons in a fixed wavelength range received by it and transmit this data to external devices and systems. The measurable wavelength range of the set photon counter must overlap with the laser wavelength range emitted by the line laser.

[0082] Step 3) Slice the number of photons collected by the photon counter in the form of time series data to obtain a time series data slice of the number of photons.

[0083] The obtained time series data slice of the number of photons is organized at a certain sampling rate and is a one-dimensional array with a certain length. At the same time, the time series data slice also includes the start time and sampling rate information of the time series data.

[0084] In this embodiment, when performing the time series data slicing of the number of photons, there is a certain overlap rate between adjacent time series data slices. On the one hand, this can increase the length of a single time series data and improve the accuracy of subsequent analysis. On the other hand, it can reduce the analysis time interval and increase the calculation frequency of water leakage fault monitoring.

[0085] Specifically, the length of the time series data slice of the number of photons adopted in this embodiment is 1 s, and the sampling frequency is 100 kHz.

[0086] Step 4) Analyze the time series data slices of the photon counts collected by each photon counter respectively, and obtain the leakage monitoring discrimination result of a single photon counter.

[0087] As Figure 4 shown, it specifically includes the following steps:

[0088] Step 41) Set a set of multi-dimensional feature discrimination methods for one-dimensional time series. The set of multi-dimensional feature discrimination methods includes discrimination methods based on root mean square value, kurtosis index, EMD decomposition features, and synchrosqueezed wavelet transform time-frequency spectrum energy features of sensitive frequency bands.

[0089] Among them, the discrimination method based on the root mean square value includes the following steps:

[0090] A1. Extract the root mean square value feature based on the time series slice data of the photon counts of a certain photon counter. Its calculation method is:

[0091] ,

[0092] where x i is the data value, N is the data volume.

[0093] Calculated in this way, a numerical root mean square value feature can be extracted from the time series slice data of a single photon count. Multiple ordered numerical root mean square value features can be extracted from the time series slice data of multiple photon counts.

[0094] A2. Set the root mean square value discrimination limit.

[0095] In this embodiment, the root mean square value discrimination limit is set to three times the standard deviation of the baseline data mean value of the baseline data. Among them, the baseline data is the multiple root mean square value features corresponding to the time series slice data of multiple photon counts within a preset time, that is . Among them, , are the average value and standard deviation of the multiple root mean square values corresponding to the time series slice data of multiple photon counts within a period of time respectively.

[0096] A3. Set the first discrimination time and the first discrimination count limit and discriminate the leakage fault.

[0097] Within the set first discrimination time, judge the number of times that the root mean square value feature calculated based on the time series slice data of multiple photon counts of this photon counter is greater than or equal to the root mean square value discrimination limit (that is ), denoted as the first number. If the first number is greater than or equal to the first discrimination count limit, it is determined that this photon counter monitors a leakage fault.

[0098] Among them, the discrimination method based on the kurtosis index includes the following steps:

[0099] B1. Extract the kurtosis index feature based on each photon number time series slice data of a certain photon counter. The calculation method is:

[0100] ,

[0101] where represents the average value.

[0102] Calculated in this way, a numerical kurtosis index feature can be extracted from a single photon number time series slice data. For multiple photon number time series slice data, multiple ordered numerical kurtosis index features can be extracted.

[0103] B2. Set the discrimination limit value of the kurtosis index.

[0104] In this embodiment, the discrimination limit value of the kurtosis index is set as the mean of the baseline data plus three times the standard deviation of the baseline data. Among them, the baseline data is multiple kurtosis index features corresponding to multiple photon number time series slice data within a preset time; that is . Among them, , are respectively the average value and the standard deviation of multiple kurtosis indexes corresponding to multiple photon number time series slice data within a period of time.

[0105] B3. Set the second discrimination time and the second discrimination times limit and discriminate the water leakage fault.

[0106] Within the set second discrimination time, judge the number of times that the kurtosis index feature calculated based on multiple photon number time series slice data of this photon counter is greater than or equal to the discrimination limit value of the kurtosis index (that is ), which is recorded as the second number of times. If the second number of times is greater than or equal to the second discrimination times limit, it is determined that the photon counter monitors a water leakage fault.

[0107] Among them, the discrimination method based on the EMD decomposition characteristic includes the following steps:

[0108] C1. Perform EMD decomposition processing on the photon number time series slice data x 1 ,x 2 ,…,x N to obtain the corresponding IMF components of each order ( c 1 ( x ), c 2 ( x ), …, cm ( x )) T , where N represents the number of data in the slice, c i ( x ) represents the i th order IMF component, m indicating that the sliced data of the photon number time series is divided into m IMF components. According to this calculation method, after calculating the sliced data of a single photon number time series, m IMF component data can be obtained.

[0109] C2, set the EMD decomposition discrimination index and the limit value of the EMD decomposition discrimination index.

[0110] Take the data of the 1st order IMF component after EMD decomposition of the sliced data of the photon number time series c 1 ( x ), and find the maximum value c 1 ( x ) in the data of the 1st order IMF component, average value and standard deviation . Take the maximum value c 1 ( x ) in the data of the 1st order IMF component of the photon number time series data as the EMD decomposition discrimination index, and take the sum of the average value and 3 times the standard deviation c 1 ( x ) in the data of the 1st order IMF component of the photon number time series data as the limit value of the EMD decomposition discrimination index , that is . That is .

[0111] It should be noted that different from the root mean square value and kurtosis index feature methods, the limit value of the EMD decomposition feature discrimination index is calculated completely independently for each sliced data of the photon number time series, that is, each independent sliced data of the photon number time series has an independent EMD decomposition feature discrimination index limit value.

[0112] C3, set the third discrimination time and the limit value of the third discrimination times and discriminate the water leakage fault.

[0113] Within the set third discrimination time, judge the EMD decomposition discrimination index calculated based on the sliced data of multiple photon number time series of this photon counter Greater than or equal to the discrimination index limit of EMD decomposition (i.e., ), which is recorded as the third number of times. If the third number of times is greater than or equal to the third discrimination number limit, it is determined that the photon counter has detected a water leakage fault.

[0114] Among them, the discrimination method based on the time-frequency spectrum energy characteristics of the sensitive band synchrosqueezed wavelet transform includes the following steps:

[0115] D1. The synchrosqueezed wavelet transform is an improved wavelet transform method that can squeeze the wavelet factor spectrum along the scale axis direction and make the energy distribution of the time-frequency spectrum more concentrated. Therefore, the time-frequency spectrum of the synchrosqueezed wavelet transform has higher aggregation and resolution compared with the general wavelet factor spectrum. Based on the time series slice data of each photon number of a certain photon counter, calculate its time-frequency spectrum characteristics of the synchrosqueezed wavelet transform represented by a two-dimensional matrix:

[0116] ,

[0117] where, T and F respectively represent the maximum number of numbers in the time and frequency dimensions. The first dimension of the obtained time-frequency spectrum of the synchrosqueezed wavelet transform is time, and the second dimension is frequency.

[0118] D2. Set the sensitive frequency band and complete the time-frequency spectrum interception.

[0119] The significance of setting the sensitive frequency band is that the change in the number of photons will cause a strong change in the time-frequency spectrum diagram within a specific frequency band range. After setting the sensitive frequency band, the change in the number of photons can be detected more sensitively and accurately. Set the lower limit and the upper limit of the sensitive frequency band, and intercept the time-frequency spectrum characteristic matrix of the synchrosqueezed wavelet transform according to the sensitive frequency band , that is, only retain the time-frequency spectrum of the synchrosqueezed wavelet transform within the sensitive frequency band range.

[0120] D3. Accumulate the intercepted time-frequency spectrum of the synchrosqueezed wavelet transform in the frequency dimension to obtain the sensitive band energy time series data , where , find the maximum value in the sensitive band energy time series data , the average value and the standard deviation . Take the maximum value of the sensitive band energy time series data as the energy characteristic discrimination index, and take the sum of the average value and 3 times the standard deviation as the discrimination index limit of the time-frequency energy characteristics , that is .

[0121] The discrimination index limit of the energy of the sensitive frequency band of the synchronous compressed wavelet transform is calculated completely independently for each slice of the photon number time series data, that is, each independent slice of the photon number time series data has an independent discrimination index limit of the energy of the sensitive frequency band of the synchronous compressed wavelet transform.

[0122] D4. Set the fourth discrimination time and the fourth discrimination times limit and discriminate the water leakage fault.

[0123] Within the set fourth discrimination time, judge the discrimination index of the energy of the sensitive frequency band of the synchronous compressed wavelet transform calculated based on multiple slices of the photon number time series data of this photon counter is greater than or equal to the time-frequency energy feature discrimination index limit (that is ), and record it as the fourth number of times. If the fourth number of times is greater than or equal to the fourth discrimination times limit, it is determined that the photon counter monitors a water leakage fault.

[0124] D5. Perform pseudo-color processing on the intercepted synchronous compressed wavelet transform time-frequency spectrum and send it into a pre-trained convolutional neural network model for discrimination to obtain the water leakage monitoring discrimination result for a single slice of the photon number time series data.

[0125] Such as Figure 5 shows the structure of the convolutional neural network model adopted in an embodiment. In other embodiments, other structures can also be adopted, and this embodiment does not make specific limitations on this.

[0126] D6. Set the fifth discrimination time and the fifth discrimination times limit and discriminate the water leakage fault.

[0127] Within the set fifth discrimination time, judge the number of times that the output result of the neural network model calculated based on multiple slices of the photon number time series data of this photon counter indicates a water leakage fault, and record it as the fifth number of times. If the fifth number of times is greater than or equal to the fifth discrimination times limit, it is determined that the photon counter monitors a water leakage fault.

[0128] Step 42) Select multiple feature discrimination methods from the set of multi-dimensional feature discrimination methods, calculate the corresponding features based on the selected feature discrimination methods, and respectively judge whether a water leakage fault occurs according to the calculated features.

[0129] In this embodiment, 5 results obtained by simultaneously using the above 4 methods are used for judgment. For different feature discrimination methods of all single photon counters, a discrimination time of 2 minutes and a times limit of 5 are uniformly adopted.

[0130] For the synchrosqueezed wavelet transform time-frequency spectrum in the sensitive frequency band, after performing pseudo-color processing on it according to the jet color map, it is scaled to a size of 512×512, and the convolutional neural network model in Figure 5 is used to achieve leakage identification, and the sensitive frequency band is set to 10 kHz to 20 kHz.

[0131] For the results of these 5 kinds of root mean square values, kurtosis indexes, EMD decomposition features, synchrosqueezed wavelet transform time-frequency spectrum energy features in the sensitive frequency band, and deep learning judgment results of the synchrosqueezed wavelet transform in the sensitive frequency band, the set weights are W = [0.2, 0.2, 0.2, 0.1, 0.3] respectively.

[0132] Step 43) Aggregate the discrimination results of multiple feature discrimination methods for a single photon counter, and judge whether the corresponding photon counter monitors a leakage fault according to the weighted sum rule.

[0133] Specifically:

[0134] For the multi-dimensional feature discrimination methods of multiple selected one-dimensional time series, set the weights of the discrimination results of different features , and ensure that , P is the number of discrimination results obtained by using multiple feature discrimination methods;

[0135] For the discrimination result output by a certain feature discrimination method, if the result is that a fault is monitored, set the discrimination result to 1, and if the result is no fault, set the result to 0. Based on the set weights and the discrimination results output by each feature discrimination method, perform weighted summation to obtain the aggregated discrimination result;

[0136] Set the limit value of the leakage monitoring discrimination result of a single photon counter , and this limit value takes a value between 0 and 1. If the aggregated discrimination result is greater than the limit value of the leakage monitoring discrimination result of a single photon counter , it is considered that the leakage monitoring result of this photon counter is faulty.

[0137] Step 5) Obtain the leakage monitoring discrimination result of the area to be detected based on the leakage monitoring discrimination result of a single photon counter.

[0138] Set the K / N voting rule, that is, within a certain time range, if more than K photon counters among N photon counters provide true leakage fault monitoring results, it is considered that a leakage fault has occurred in this area to be detected.

[0139] Example 2

[0140] Based on Embodiment 1, this embodiment provides an installation configuration scheme for a line laser and a photon counter for regional water leakage monitoring. By reasonably arranging the line laser and the photon counter, water leakage fault monitoring in a specific area of the converter valve hall is achieved.

[0141] In this configuration of the line laser and the photon counter, the configuration goal is to achieve coverage of regional water leakage monitoring with fewer photon counters. The water leakage area to be detected in this embodiment is a specific square area in space, that is, this area has boundaries in the horizontal direction. The configuration method includes two key contents: configuring the line laser and configuring the photon counter.

[0142] (1)Configuration of the line laser

[0143] The setting of the line laser includes the following steps:

[0144] S101, Determine the area to be detected and the positions where the line laser can be installed: According to the on-site conditions, determine the horizontal boundaries of the water leakage area to be detected and the position range where the line laser can be installed. Among them, the positions where the line laser can be installed are generally on the walls or frameworks of the building, represented as one or several line segments.

[0145] S102, Determine the installation position of the line laser: As Figure 2 shown, draw the perpendicular bisector of the short side b of the rectangular water leakage area to be detected, which forms an intersection point O with the line segment describing the positions where the line laser can be installed, and use the intersection point O as the installation position of the line laser.

[0146] S103, Determine the fan angle and effective distance of the line laser: The parameters of the line laser include the fan angle and the effective distance L . The parameters of the line laser meet the following conditions: 1) The effective distance L must exceed the maximum value of the distances from the installation position O of the line laser to all positions within the water leakage area to be detected; 2) The laser fan angle meets the requirement that the effective working fan-shaped range of the line laser covers the rectangular water leakage area to be detected, that is, , where b is the length of the short side of the rectangular water leakage area to be detected, and d is the distance between the installation position O of the line laser and the short side b of the rectangular water leakage area to be detected.

[0147] S104, Determine the installation angle of the line laser: Set the vertical installation angle of the line laser to be horizontal, that is, the plane of the fan-shaped column formed by the laser trajectory is parallel to the horizontal plane. At the same time, set the horizontal installation angle of the line laser to face the water leakage area to be detected, that is, the angular bisector of the fan-shaped cross-section of the fan-shaped column formed by the laser trajectory is parallel to the short side bcoincides with the perpendicular bisector.

[0148] In a preferred embodiment, as Figure 2 , Figure 3 shown, a line laser and a photon counter are installed on the wall opposite to the converter valve area. The distance between the line laser and the area to be detected for water leakage d = 6 m. The wavelength range of the line laser used is 635 ± 15 nm. The photon counter used has a wavelength range of 635 ± 5 nm, meeting the requirement that the detectable wavelength range of the photon counter is less than or equal to the wavelength range of the line laser. The effective working range L of the line laser used is 30 m, and the laser fan angle = 30°.

[0149] In the embodiment provided by the present invention, the length of the photon number time series data slice used is 1 s, and the sampling frequency is 100 kHz.

[0150] (2) Configuration of the photon counter

[0151] The configuration of the photon counter includes the following steps:

[0152] S201, determining the installable positions of the photon counter: According to the on-site conditions, determine the positions where the photon counter can be installed. The positions where the photon counter can be installed are on the walls or frameworks of the building, represented as one or several line segments, and are horizontally aligned with the installable positions of the line laser.

[0153] S202, based on the installable positions of the photon counter, configure multiple photon counters in the horizontal direction, with the receiving probe directions of all photon counters facing the area to be detected for water leakage. In the vertical direction, there should be a certain height difference h between the installation height of the photon counter and the line laser, either higher than the line laser or lower than the line laser, as Figure 3 shown. In this embodiment, the height difference h between the photon counter and the line laser needs to satisfy not less than 0.5 m. In addition, set the installation angle attitude of the photon counter to be parallel to the horizontal plane.

[0154] In a preferred embodiment, as Figure 2 , Figure 3 shown, a total of 8 photon counters are installed on the wall. The height difference h between the photon counter and the line laser is 0.5 m. The 8 photon counters used are installed in the way of 4 on each of the upper and lower layers.

[0155] Embodiment 3

[0156] This embodiment provides a converter station valve hall water leakage monitoring system based on a photon counter for implementing the method described in Embodiment 1 above, as Figure 6As shown, the system includes a line laser, multiple photon counters, a control unit, a data processing unit, a communication unit, and a human-machine interface. Among them,

[0157] The line laser is used to achieve non-stop scanning and irradiating the area to be detected for water leakage;

[0158] The photon counters are used to collect the change in the number of photons in the area to be detected for water leakage, and obtain the time-series data of the number of photons;

[0159] The control unit is used to achieve the coordinated control of the line laser, photon counters, and data processing unit;

[0160] The data processing unit is used to slice and analyze the time-series data of the number of photons collected by the photon counters, and output the discrimination result of water leakage monitoring;

[0161] The communication unit is used to achieve the internal and external communication of the water leakage monitoring system in the converter station valve hall;

[0162] The human-machine interface is used to achieve the interaction between personnel and the water leakage monitoring system in the converter station valve hall.

[0163] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the described units / modules can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated here.

[0164] In this embodiment, an ordinary microcomputer is used as the control unit and computing unit. Among them, the communication between the microcomputer and the line laser is implemented through an RS232 port, and the communication with the photon counters is implemented through an RJ45 port Ethernet. Graphical software programs are combined with a display, a mouse, and a keyboard to achieve human-computer interaction.

[0165] The preferred specific embodiments of the present invention have been described in detail above. It should be understood that those of ordinary skill in the art can make many modifications and variations according to the concept of the present invention without creative labor. Therefore, all technical solutions that can be obtained by those skilled in the art in this technical field based on the concept of the present invention through logical analysis, reasoning, or limited experiments on the basis of the prior art should be within the protection scope determined by the claims.

Claims

1. A method for monitoring water leakage in a converter station valve hall based on a photon counter, characterized in that: The following steps are involved: A line laser and multiple photon counters are set in the leakage area to be detected, and the line laser is used to illuminate the leakage area to be detected in the valve hall of the converter station, and the number of photons received by the photon counter within a fixed wavelength range is measured. The measurable wavelength range of the photon counter overlaps with the wavelength range of the laser emitted by the line laser; Slice the number of photons collected by the photon counter in the form of time series data to obtain photon number time series data slices; The photon number time series data slices collected by each photon counter are analyzed respectively to obtain the water leakage monitoring and discrimination result of a single photon counter, and the water leakage monitoring and discrimination result of the water leakage area to be detected is obtained based on the water leakage monitoring and discrimination result of the single photon counter.

2. According to claim 1, a method for monitoring water leakage in a converter station valve hall based on a photon counter is characterized in that: The laser track emitted by the set line laser is a fan-shaped column with a preset thickness, and the laser track covers the water leakage area to be detected; When the water leakage area to be detected is a rectangular area, the setting of the line laser includes the following steps: Determine the area to be detected and the location where the line laser can be installed: according to the site conditions, determine the horizontal boundary of the area to be detected for water leakage and the location range where the line laser can be installed. The location where the line laser can be installed is on the wall or frame of the building, represented by one or more line segments; Determine the installation position of the line laser: draw a perpendicular midline of the short side of the rectangular leak area to be detected, and form an intersection with the line segment describing the position where the line laser can be installed, and use the intersection as the position for installing the line laser; Determine the fan angle and effective distance of the line laser: The parameters of the line laser include the fan angle and effective distance L , the parameters of the line laser meet the following conditions: 1) effective distance L The maximum value of the distance from the installation position of the line laser to all positions in the leak area to be detected; 2) Laser fan angle The effective working sector range of the line laser covers the rectangular leak area to be detected, that is, ,in, b is the length of the short side of the rectangular leak area to be detected, d The distance between the installation position of the line laser and the short side of the rectangular leak area to be detected; Determine the installation angle of the line laser: set the vertical installation angle of the line laser to horizontal, that is, the plane of the fan-shaped column formed by the laser trajectory is parallel to the horizontal plane, and at the same time set the horizontal installation angle of the line laser to be perpendicular to the leaking area to be detected, that is, the angle bisector of the fan-shaped section of the fan-shaped column formed by the laser trajectory coincides with the perpendicular bisector of the short side of the rectangular area to be detected.

3. According to claim 1, a method for monitoring water leakage in a converter station valve hall based on a photon counter is characterized in that: The setting of the photon counter comprises the following steps: Determine the installable position of the photon counter: determine the installable position of the photon counter according to the site conditions. The installable position of the photon counter is on the wall or frame of the building, represented by one or more line segments, and is consistent with the horizontal position of the installable line laser; Based on the installable positions of the photon counters, multiple photon counters are configured in the horizontal direction, with the receiving probes of all photon counters facing the leakage area to be detected; in the vertical direction, the height difference between the installation height of the photon counter and the line laser is set to be greater than a preset threshold; the installation angle of the photon counter is set to be parallel to the horizontal plane.

4. According to claim 1, a method for monitoring water leakage in a converter station valve hall based on a photon counter is characterized in that: The difference between the upper and lower limits of the laser wavelength emitted by the line laser does not exceed 50nm.

5. The method for monitoring water leakage in the valve hall of a converter station based on a photon counter according to claim 1 is characterized in that: The photon counter can measure a wavelength range that is less than or equal to the wavelength range of the laser emitted by the line laser.

6. The method for monitoring water leakage in the valve hall of a converter station based on a photon counter according to claim 1 is characterized in that: When slicing the time series data, adjacent time series data slices are made to have partially overlapping data according to a preset overlap rate.

7. The method for monitoring water leakage in the valve hall of a converter station based on a photon counter according to claim 1 is characterized in that: The photon number time series data slice includes a one-dimensional time series array with a preset length, organized according to a preset sampling rate, the start time of the time series data, and the sampling rate information; The method of respectively analyzing the photon number time series data slices collected by each photon counter and obtaining the water leakage monitoring and identification result of a single photon counter specifically includes the following steps: A set of multidimensional feature discrimination methods for a one-dimensional time series is set, wherein the set of multidimensional feature discrimination methods includes a discrimination method based on a root mean square value, a kurtosis index, an EMD decomposition feature, and a spectrum energy feature of a sensitive band synchronous compression wavelet transform; Selecting multiple feature discrimination methods from a set of multidimensional feature discrimination methods, calculating corresponding features based on the selected feature discrimination methods, and judging whether a water leakage fault occurs according to the calculated features; The discrimination results of multiple feature discrimination methods for a single photon counter are summarized, and the weighted summation rule is used to determine whether the corresponding photon counter has detected a water leakage fault.

8. The method for monitoring water leakage in the valve hall of a converter station based on a photon counter according to claim 7 is characterized in that: The discrimination method based on the root mean square value includes the following steps: Extract the root mean square value feature based on each photon number time series slice data of a certain photon counter; The root mean square value discrimination limit is set to be the baseline data mean plus three times the baseline data standard deviation, wherein the baseline data is a plurality of root mean square value features corresponding to a plurality of photon number time series slice data within a preset time; Setting a first discrimination time and a first discrimination number limit and discriminating a water leakage fault: within the set first discrimination time, judging the number of times that the root mean square value feature calculated based on multiple photon number time series slice data of the photon counter is greater than or equal to the root mean square value discrimination limit, which is recorded as the first number; if the first number is greater than or equal to the first discrimination number limit, it is judged that the photon counter detects a water leakage fault; The discrimination method based on kurtosis index includes the following steps: Extract the kurtosis index feature based on each photon number time series slice data of a certain photon counter; The kurtosis index determination limit is set to be the baseline data mean plus three times the baseline data standard deviation, wherein the baseline data is a plurality of kurtosis index features corresponding to a plurality of photon number time series slice data within a preset time; Setting a second discrimination time and a second discrimination number limit and discriminating a water leakage fault: within the set second discrimination time, judging the number of times that the kurtosis index feature calculated based on the multiple photon number time series slice data of the photon counter is greater than or equal to the kurtosis index discrimination limit, recorded as the second number, if the second number is greater than or equal to the second discrimination number limit, it is judged that the photon counter detects a water leakage fault; The discrimination method based on EMD decomposition characteristics includes the following steps: Slice the photon number time series data[ x 1 ,x 2 ,…,x N ] to perform EMD decomposition and obtain the corresponding IMF components of each order ( c 1 ( x ), c 2 ( x ),…, c m ( x )) T ,in, N Indicates the number of data in the slice, c i ( x ) indicates the i The order IMF component, m The photon number time series slice data is divided into m IMF components; Set the EMD decomposition discrimination index and EMD decomposition discrimination index limit: Take the first-order IMF component data after EMD decomposition of the photon number time series slice data c 1 ( x ), obtain the first-order IMF component data c 1 ( x ) ,average value and standard deviation , the first-order IMF component data of the photon number time series data c 1 ( x ) As the EMD decomposition indicator, the first-order IMF component data of the photon number time series data is c 1 ( x ) and 3 times the standard deviation The sum is used as the EMD decomposition judgment index limit ,Right now ; Set the third discrimination time and the third discrimination number limit and judge the water leakage fault: within the set third discrimination time, judge the EMD decomposition discrimination index calculated based on the multiple photon number time series slice data of the photon counter Greater than or equal to the EMD decomposition judgment index limit The number of times is recorded as the third number. If the third number is greater than or equal to the third discrimination number limit, it is determined that the photon counter detects a water leakage fault; The method for distinguishing the spectrum energy characteristics based on the sensitive band synchronous compression wavelet transform includes the following steps: Based on the time series slice data of each photon number of a photon counter, the time-frequency spectrum characteristics of the synchronous compression wavelet transform represented by a two-dimensional matrix are calculated: ， in, T and F They represent the maximum number of numbers in the time and frequency dimensions respectively. The first dimension of the spectrum obtained by synchronous compression wavelet transform is time, and the second dimension is frequency. Set the sensitive frequency band and complete the spectrum capture: set the lower limit of the sensitive frequency band and upper limit , and the spectral feature matrix of synchronous compression wavelet transform is intercepted according to the sensitive frequency band , that is, only the synchronous compression wavelet transform time-frequency spectrum within the sensitive frequency band is retained; The truncated synchronous compression wavelet transform time spectrum is accumulated in the frequency dimension to obtain the sensitive frequency band energy time series data ,in , obtain the sensitive frequency band energy time series data The maximum value in ,average value and standard deviation , the sensitive frequency band energy time series data The maximum value of As an energy feature discrimination index, the average value and 3 times the standard deviation The sum is used as the limit value of the time-frequency energy characteristic discrimination index ,Right now ; Set the fourth discrimination time and the fourth discrimination number limit and judge the water leakage fault: within the set fourth discrimination time, judge the discrimination index of the energy characteristic of the sensitive frequency band of the synchronous compression wavelet transform calculated based on the multiple photon number time series slice data of the photon counter Greater than or equal to the time-frequency energy characteristic discrimination index limit The number of times is recorded as the fourth number. If the fourth number is greater than or equal to the fourth discrimination number limit, it is determined that the photon counter detects a water leakage fault; The intercepted synchronous compression wavelet transform time spectrum is processed with pseudo color and sent to the pre-trained convolutional neural network model for discrimination, and the water leakage monitoring discrimination result for a single photon number time series data slice is obtained; Set the fifth judgment time and the fifth judgment number limit and judge the water leakage fault: within the set fifth judgment time, judge that the output result of the neural network model calculated based on the multiple photon number time series slice data of the photon counter is the number of times the water leakage fault occurs, recorded as the fifth number; if the fifth number is greater than or equal to the fifth judgment number limit, it is determined that the photon counter has detected a water leakage fault.

9. The method for monitoring water leakage in the valve hall of a converter station based on a photon counter according to claim 7 is characterized in that: The method of summarizing the discrimination results of a single photon counter using multiple feature discrimination methods and judging whether the corresponding photon counter has detected a water leakage fault according to the weight summation rule is as follows: For the multidimensional feature discrimination method of multiple selected one-dimensional time series, the weights of the discrimination results of different features are set respectively. , and guarantee , P is the number of discrimination results obtained by using multiple feature discrimination methods; For the discrimination result output by a certain feature discrimination method, if the result is a fault detected, the discrimination result is set to 1, and if the result is no fault, the result is set to 0. The weighted sum is performed based on the set weight and the discrimination result output by each feature discrimination method to obtain the summary discrimination result; A limit value for the water leakage fault monitoring judgment result of a single photon counter is set. If the summary judgment result is greater than the limit value for the water leakage fault monitoring judgment result of a single photon counter, the water leakage monitoring result of the photon counter is considered to be faulty.

10. A converter station valve hall water leakage monitoring system based on a photon counter, used to implement the method according to any one of claims 1 to 9, characterized in that: The system includes a line laser, a plurality of photon counters, a control unit, a data processing unit, a communication unit and a human-machine interface, wherein: The line laser is used to realize non-interval scanning and irradiation of the water leakage area to be detected; The photon counter is used to collect the changes in the number of photons in the leaking area to be detected, and obtain the time series data of the number of photons; The control unit is used to realize the coordinated control of the line laser, the photon counter, and the data processing unit; The data processing unit is used to slice and analyze the photon number time series data collected by the photon counter, and output the water leakage monitoring and discrimination result; The communication unit is used to realize the communication inside and outside the converter station valve hall water leakage monitoring system; The human-machine interface is used to realize the interaction between personnel and the valve hall water leakage monitoring system of the converter station.

Images