A system for intelligent identification and processing of deep-sea instrument subsidence process data

Abstract

This invention discloses an intelligent identification and processing system for depth gauge settling process data, belonging to the field of marine fisheries engineering and data processing technology. The system includes: a data input and configuration module for receiving raw data files and configuring the starting point parameters; a data parsing and preprocessing module for identifying the valid starting position of data and converting it to a standard format; an instantaneous velocity calculation module for calculating and smoothing instantaneous settling velocity; an adaptive segmentation and feature extraction module for automatically segmenting independent settling process data segments by monitoring depths continuously exceeding a first threshold to mark the starting point, tracking the maximum depth point, and marking the ending point when the depth falls back to a level less than a second threshold; and a hierarchical statistics and visualization module for performing velocity statistics according to preset depth intervals and generating a dual-axis chart. This invention achieves fully automated processing of fishing gear settling data, significantly improving efficiency and accuracy, and enabling standardized output.

Description

Technical Field

[0001] This invention relates to the field of marine fisheries engineering and data processing technology, and in particular to an intelligent identification and processing system for depth gauge settling process data, which is used to analyze time series data collected by depth sensors and automatically evaluate the settling performance of fishing gear or underwater devices. Background Technology

[0002] In fishing gear performance studies (such as trawl sinking and longline fishing performance testing), depth sensors (such as Star-Oddi DST) are typically used to record the device's depth data over time. The traditional approach involves researchers manually exporting CSV data; manually finding the start and end points of each cast in Excel; manually calculating the depth difference between adjacent time points to obtain the instantaneous velocity; and using plotting software (such as Origin or Matlab) to create separate graphs for each experiment. Currently, the most common solution is to use general-purpose data processing software (Excel) combined with general-purpose plotting tools. Users need to visually determine the valid segments of the data, manually remove invalid data (airborne data) recorded by the device, and repeatedly establish coordinate axes and calculation formulas for each experiment.

[0003] However, existing technologies have the following problems:

[0004] 1. Inefficient: When the sensor continuously records dozens of experimental data, manually segmenting the data is extremely time-consuming and prone to errors.

[0005] 2. Lack of standardization: When manually calculating the settling velocity and statistically analyzing the average velocity of specific water layers (such as 0-5m, 10-20m), inconsistent results can easily occur due to differences in the range selected by the individual.

[0006] 3. Cumbersome visualization: Generating dual-axis charts (depth and velocity in the same graph) that meet the requirements of scientific journals is a complex process that makes it difficult to produce in batches. Summary of the Invention

[0007] This invention addresses the aforementioned problems by providing an intelligent identification and processing system for depth gauge settling process data. It aims to solve the issues of low efficiency, poor segmentation accuracy, and cumbersome statistical analysis in existing manual processing of fishing gear depth data. Through an automated data processing method, it achieves intelligent identification, automatic segmentation, multi-dimensional velocity statistics, and batch visualization output that meets academic standards for continuous time-series depth data.

[0008] This invention provides an intelligent identification and processing system for depth gauge settlement process data, comprising: a data input and configuration module for receiving a raw data file containing time and depth information, and configured with parameters for determining the starting point of data reading; a data parsing and preprocessing module for parsing the raw data file to identify the starting position of valid data, converting the data into a standard time series format and numerical depth data, and obtaining converted time and depth data; an instantaneous velocity calculation module for calculating the corresponding instantaneous settlement velocity data based on the converted time and depth data; and an adaptive segmentation and feature extraction module for extracting features from continuous depth data. The system automatically segments independent settlement process data segments from the depth data. By monitoring depth data, it marks the starting point when the depth continuously exceeds a first preset threshold. It then tracks depth changes until the maximum depth point is identified. After that, when the depth falls back to a point where the difference from the starting point is less than a second preset threshold, it marks the ending point, thus extracting a complete settlement process. The layered statistics and visualization module is used to perform velocity statistics on the settlement process data segments according to at least one preset depth interval and generate charts. It performs settlement velocity statistics according to preset depth intervals and generates a dual-axis chart that simultaneously displays the depth curve and velocity curve on the horizontal axis at the same time to achieve data visualization.

[0009] Preferably, the data parsing and preprocessing module includes: a multi-encoding attempt unit, used to attempt to read the original data file in multiple character encoding formats; and a header intelligent positioning unit, connected to the multi-encoding attempt unit, used to determine the starting position of the valid data row by traversing the contents of the first predetermined number of rows of the original data file and identifying the row number where the predetermined keyword is located.

[0010] Preferably, the instantaneous velocity calculation module includes: a differential calculation unit for calculating the ratio of depth difference to time difference between adjacent time points to obtain the original instantaneous velocity; and a smoothing filtering unit for denoising and smoothing the original instantaneous velocity to output stable velocity curve data.

[0011] Preferably, the adaptive segmentation and feature extraction module includes: a threshold determination unit, used to monitor depth data, and determine the depth position as the starting point when the depth is continuously greater than a first preset threshold; a peak backtracking unit, used to track the maximum depth during a single deployment process, thereby determining the maximum depth point, and locking the depth data back to a point where the difference between the depth and the starting point is less than a second preset threshold and marking it as the ending point; and a validity verification unit, used to verify the segmented data segments, extract data fragments from the starting point to the ending point, and if the maximum depth of the fragment is lower than the minimum effective depth threshold or the amount of data contained in the data segment is lower than the minimum quantity threshold, then it is determined as invalid data and discarded; otherwise, it is marked as a valid sedimentation process data segment.

[0012] Preferably, the adaptive segmentation and feature extraction module uses state machine logic to automatically segment independent settlement process data segments from continuous depth data. The state machine includes: a waiting state, maintained when the depth data is less than a first preset threshold; a trigger state, entered when the depth data is continuously greater than or equal to the first preset threshold, and the time corresponding to the current data point is recorded as the starting point of the settlement process; a peak determination state, started after entering the trigger state, used to continuously analyze the depth data to identify local maximum values ​​or determine whether the depth exceeds a large depth threshold, thereby determining the maximum depth point; and an end determination state, entered after the maximum depth point is identified, used to record the current point as the end point when the depth data falls back to a depth less than a second preset threshold.

[0013] Preferably, the hierarchical statistics and visualization module includes: a Boolean mask statistics unit for calculating and statistically analyzing the average velocity within a preset depth range; and a dual-axis plotting engine unit for generating a coordinate system with a shared time axis, the coordinate system including a first vertical axis for representing depth values ​​and a second vertical axis for representing velocity values, and outputting the data according to a preset style.

[0014] Preferably, the statistical operations performed by the Boolean mask statistical unit are equal-segment statistics and / or fixed-depth statistics; wherein, equal-segment statistics are used to divide a complete settlement process data segment into M segments in chronological order, and calculate the average velocity within each segment, where M is an integer greater than 1; fixed-depth statistics are used to calculate the average velocity and sample size corresponding to each depth range according to N pre-set depth ranges, where N is an integer greater than 0. When performing fixed-depth statistics, if the maximum depth of the settlement process data segment does not reach the predetermined depth range, the statistical results of the corresponding range are marked as invalid or without data.

[0015] This invention provides an intelligent identification and processing method for sedimentation process data from a depth gauge, characterized by the following steps: Step S1, Intelligent data reading and head recognition: Reading the original data file, identifying and extracting valid time and depth data; Step S2, Data preprocessing and velocity calculation: Standardizing the time and depth data, calculating the instantaneous sedimentation velocity based on the change of depth data over time, and smoothing the instantaneous sedimentation velocity; Step S3, Automatic sedimentation process segmentation: Traversing continuous time series data, identifying the start point, maximum depth point, and end point of the sedimentation process through state machine logic, thereby extracting independent sedimentation process data segments; Step S4, Velocity hierarchical analysis: Performing velocity statistical analysis on each sedimentation process data segment according to at least one preset depth interval; Step S5, Chart generation and output: Generating a dual-axis chart for each sedimentation process data segment, simultaneously displaying the depth curve and velocity curve on the same horizontal axis, and exporting the statistical results and charts.

[0016] Preferably, in step S4, the velocity stratification analysis includes equal-segment statistics and / or fixed-depth statistics. Equal-segment statistics divide a complete settlement process data segment into M segments in chronological order and calculate the average velocity within each segment, where M is an integer greater than 1. Fixed-depth statistics calculate the average velocity and sample size within each of N predetermined depth ranges, where N is an integer greater than 0. When performing fixed-depth statistics, if the maximum depth of the settlement process data segment does not reach the predetermined depth range, the statistical results for the corresponding range are marked as invalid or without data.

[0017] Technical effect

[0018] Compared with existing technologies, the intelligent identification and processing method and system for depth gauge settling process data in this invention has the following technical advantages:

[0019] 1. Extremely high processing efficiency: It can process files containing tens of thousands of lines of data and dozens of repeated experiments within one minute, automatically splitting and generating independent reports, which is dozens of times more efficient than manual processing.

[0020] 2. Precise intelligent segmentation: Through depth threshold and peak backtracking algorithm, it can accurately eliminate invalid fluctuations of the sensor in the air or near the water surface, and extract only the valid experimental segments.

[0021] 3. Multi-dimensional data insights: Automatically calculates stratification speeds (S-5m, 10-20m, etc.), providing direct data support for analyzing the differences in the settling posture of nets in different water layers.

[0022] 4. Standardized output: Directly generates charts that meet the format requirements of high-level journals such as Nature, eliminating the need for subsequent enhancements and significantly lowering the barrier to entry for scientific chart creation. Attached Figure Description

[0023] The above and other objects, features, and advantages of this application will become more apparent from the following detailed description of the embodiments in conjunction with the accompanying drawings. The drawings are provided to further illustrate the embodiments of this application and form part of the specification. They are used together with the embodiments of this application to explain the application and do not constitute a limitation thereof. In the drawings, the same reference numerals generally represent the same components or steps.

[0024] Figure 1 This is a diagram of the intelligent identification and processing system for sedimentation process data from a depth gauge in Embodiment 1 of the present invention.

[0025] Figure 2 This is a schematic diagram of the main operation interface of the intelligent identification and processing system for sedimentation process data of the depth gauge in Embodiment 2 of the present invention;

[0026] Figure 3This is a schematic diagram of selecting the target file in Embodiment 2 of the present invention;

[0027] Figure 4 This is a diagram illustrating the data processing and chart generation results in Embodiment 2 of the present invention.

[0028] Figure 5 This is a schematic diagram of the export settings in Embodiment 2 of the present invention; Detailed Implementation

[0029] To make the technical means, creative features, objectives and effects of the present invention easy to understand, the following embodiments, in conjunction with the accompanying drawings, specifically illustrate the intelligent identification and processing system for sedimentation process data of a depth gauge according to the present invention.

[0030] Example 1

[0031] This embodiment provides an intelligent identification and processing system for sedimentation process data from a depth gauge.

[0032] Figure 1 This is a diagram illustrating the architecture of the intelligent identification and processing system for sedimentation process data from a depth gauge in an embodiment of the present invention.

[0033] like Figure 1 As shown, the intelligent identification and processing system for depth gauge settling process data in this embodiment includes:

[0034] The data input and configuration module 10 serves as the system's user interface, used to receive raw data files containing time and depth information, and is configured with parameters to determine the starting point for data reading.

[0035] In this embodiment, the data input and configuration module 10 includes a file path acquisition unit and a parameter setting unit. The file path acquisition unit is used to receive raw depth sensor data files in CSV format from external input. The parameter setting unit is connected to the file path acquisition unit, allowing users to manually set the number of skipped rows or select the "automatic recognition" mode to determine the starting point for data reading, thereby adapting to file headers containing non-standard metadata exported from sensors of different brands.

[0036] The data parsing and preprocessing module 20 is responsible for the standardization and cleaning of the data. It is used to parse the original data file to identify the starting position of the valid data, convert the data into standard time series format and numerical depth data, and obtain the converted time data and depth data.

[0037] In this embodiment, the data parsing and preprocessing module 20 incorporates a multi-encoding attempt unit (supporting GBK, UTF-8, etc.) and a header intelligent positioning unit. The encoding attempt unit is used to attempt to read the raw data file in various character encoding formats. The header intelligent positioning unit is connected to the multi-encoding attempt unit, and identifies valid data starting lines by traversing the first 100 lines of the file or identifying lines containing the keywords "Time / Date" or "time". Subsequently, the data is converted into standard time series format and numerical deep data, and invalid null values ​​(NaN) are removed.

[0038] The instantaneous velocity calculation module 30 calculates the settlement velocity based on the differential algorithm. It calculates the corresponding instantaneous settlement velocity data based on the converted time data and depth data.

[0039] In this embodiment, the instantaneous velocity calculation module 30 includes a difference calculation unit and a smoothing filtering unit. The difference calculation unit calculates the ratio of the depth difference to the time difference between adjacent time points to obtain the original instantaneous velocity. The smoothing filtering unit uses a sliding window algorithm to denoise and smooth the original instantaneous velocity, outputting stable velocity curve data.

[0040] The adaptive segmentation and feature extraction module 40 uses state machine logic to automatically cut out independent experimental groups from continuous data, that is, to automatically segment independent settlement process data segments from continuous depth data; by monitoring depth data, when the depth continuously exceeds the first preset threshold, it is marked as the starting point; then the depth change is tracked until the maximum depth point is identified; thereafter, when the depth falls back to the point where the difference from the starting point depth is less than the second preset threshold, it is marked as the ending point, thereby extracting a complete settlement process (Group).

[0041] In this embodiment, the adaptive segmentation and feature extraction module 40 includes a threshold determination unit, a peak backtracking unit, and a validity verification unit. The threshold determination unit monitors depth data. When the depth continuously exceeds a first preset threshold (1 meter in this embodiment), the depth position is determined as the starting point (ingress point). The peak backtracking unit tracks the maximum depth during a single deployment (greater than 30 meters or a local maximum in this embodiment), thereby determining the maximum depth point and marking the point where the depth data falls back to a depth less than a second preset threshold (28.57 m in this embodiment) as the endpoint (exit point). The validity verification unit verifies the segmented data segments, extracting data fragments from the starting point to the endpoint. If the maximum depth of the fragment is lower than the minimum effective depth threshold (1 m in this embodiment) or the data amount contained in the fragment is lower than the minimum quantity threshold (5 groups in this embodiment), it is determined as an invalid fluctuation and discarded; otherwise, it is marked as a valid "experimental group."

[0042] The stratified statistics and visualization module 50 performs velocity statistics on specific water layers for the extracted experimental groups and generates charts. For the data segment of the settlement process, it performs velocity statistics according to specific depth intervals and generates charts; it performs settlement velocity statistics according to a preset depth interval and generates a double-y-axis chart that synchronously displays the depth curve and the velocity curve under the same time horizontal axis to achieve data visualization.

[0043] In this embodiment, the stratified statistics and visualization module 50 includes a boolean mask statistics unit and a dual-axis plotting engine unit. The boolean mask statistics unit automatically calculates the average velocity of the interval according to a preset depth interval (such as 0 - 5m, 10 - 20m). The dual-axis plotting engine unit generates a coordinate system with a shared time axis based on the Matplotlib library. The coordinate system includes a left axis (depth value) and a right axis (velocity value), and outputs according to a preset style (such as removing the grid and unifying the font).

[0044] The implementation steps of the intelligent recognition and processing system for the depth gauge settlement process data in this embodiment are as follows:

[0045] Step S1, intelligent data reading and header recognition: The system reads the original data file in CSV format and has a built-in intelligent traversal algorithm. It attempts to decode through a preset encoding list and automatically scans the first 100 lines of the file to identify the line containing keywords such as "Time", "Date", or "时间" as the starting line of the header; if no keyword is found, it locates the data starting point by identifying the data feature line containing numbers and delimiters, so as to adapt to non-standard format files exported by different brand sensors.

[0046] Step S2, data preprocessing and velocity calculation: Clean the read data, convert the time field to the standard datetime format, convert the depth field to a numeric type, and剔除 missing values. On this basis, calculate the instantaneous settlement velocity: use the difference method to calculate the ratio of the depth difference to the time difference between adjacent time points, and use a sliding window (the window size in this embodiment is 5) to smooth the instantaneous velocity to eliminate data jitter caused by sensor noise.

[0047] Step S3, automatic segmentation of the settlement process: The system traverses the continuous time series data and uses state machine logic to automatically identify each independent "release - settlement - recovery" process (i.e., a "group"), thereby automatically segmenting the independent settlement process data segment. The state machine includes:

[0048] The waiting state, traversing the data and ignoring data with a depth value less than a set threshold (such as 1 meter) (regarded as invalid data on the deck or water surface);

[0049] Note: There is a Chinese character "剔除" in the original text which is not recognized in the provided rules. I assume it should be "剔除" and translated it as "剔除". If this is not correct, please clarify.Triggering state: When a depth value is detected to be continuously greater than or equal to the threshold, it is marked as the starting point (StartIndex) of the current group.

[0050] In the peak determination state, the system continues to traverse after the starting point, and dynamically finds the maximum depth point (PeakIndex) for this deployment by comparing the current depth with the depths of the previous and next points, or by identifying whether the depth exceeds the maximum depth threshold (30 meters in this embodiment).

[0051] The judgment state ends. After the maximum depth point is identified, the search proceeds backward from the peak point until the depth value drops back to a depth less than the second preset threshold (28.57m in this embodiment). The current point is then recorded as the end point.

[0052] Validity verification: Extract the data segment from the start point to the end point. If the maximum depth of the segment is lower than the minimum effective depth threshold (1m in this embodiment) or the amount of data contained in the segment is lower than the minimum number threshold (5 groups in this embodiment), it is determined to be an invalid fluctuation and is removed; otherwise, it is marked as a valid "experimental group".

[0053] Step S4, Speed ​​Stratification Analysis: For each extracted valid experimental group, the system automatically performs stratified statistics:

[0054] Equal segmentation statistics: Divide a complete settlement process data segment into 5 equal parts in chronological order, and calculate the average velocity within each segment.

[0055] Depth statistics: Based on depth intervals (e.g., surface - 5m, surface - 10m, 10m-20m, 20m-maximum depth), a Boolean mask is used to filter corresponding data rows, and the average settlement velocity and sample size for each interval are calculated. If the maximum depth of a certain data set does not meet the requirements of a specific interval (in this example, it does not reach 20m), the system automatically marks it as "no data".

[0056] Step S5, Chart Generation and Output: Generate a dual-axis chart for each data segment of the settlement process, simultaneously displaying the depth and velocity curves on the horizontal axis at the same time, and export the statistical results and charts. Specifically:

[0057] Using the Matplotlib library, a plotting canvas was constructed to generate dual Y-axis charts for each experimental group:

[0058] • Plot a depth-time curve on the left Y-axis (with data point markers);

[0059] • Plot a velocity-time curve on the right Y-axis (different colors to distinguish them);

[0060] • The chart style is preset to a scientific journal style (removing grids, adjusting scale orientation, and unifying font).

[0061] Finally, the statistical results of all groups are summarized and exported as an Excel report, and the corresponding analysis charts are saved in batches as image files.

[0062] Example 2

[0063] This embodiment uses Python to implement the intelligent identification and processing system for the sedimentation process data of the depth gauge in Embodiment 1.

[0064] Figure 2 This is a schematic diagram of the main operation interface of the intelligent identification and processing system for sedimentation process data of the depth gauge in an embodiment of the present invention.

[0065] Figure 3 This is a schematic diagram illustrating the selection of a target file in an embodiment of the present invention.

[0066] Figure 4 This is a diagram illustrating the data processing and chart generation results in an embodiment of the present invention.

[0067] Figure 5 This is a schematic diagram of the export settings in an embodiment of the present invention.

[0068] like Figures 2-5 As shown, this embodiment is written in Python and uses the PyQt5 framework to build the user graphical interface (GUI).

[0069] 1. Background thread design: Create a DataWorker class that inherits from QThread to perform time-consuming data reading and algorithm calculations in the background to prevent UI lag.

[0070] 2. Segmented logic implementation:

[0071] Set the ready_to_start flag. When current_depth < 1, set ready_to_start = True;

[0072] Record start_idx when ready_to_start is true and current_depth >= 1;

[0073] Use a loop to find d_now > 30 or a depth inflection point as peak_idx;

[0074] Find the point that returns to the starting depth from the peak point and use it as the real_end;

[0075] Use df.loc[real_start: real_end] to extract a subset of data and store it in the processed_groups list.

[0076] 3. Visual implementation:

[0077] Use matplotlib's object-oriented interface. Set ax1 to display depth (black solid dot), and ax2 = ax1.twinx() to display speed (red solid line).

[0078] Configure plt.rcParams to adapt to the display of Chinese fonts on different operating systems (Windows / Mac) to ensure that the text in the charts is clear.

[0079] 4. Interaction and Export:

[0080] The interface provides a "skip row number" setting, allowing users to manually adjust the starting point for reading non-standard CSV files.

[0081] Provide an "Export" button, iterate through all processed grouped data, write to Excel using pandas, and repeatedly call plotting functions to save PNG images.

Claims

1. A system for intelligent identification and processing of sedimentation process data from a depth gauge, characterized in that, include: The data input and configuration module is used to receive raw data files containing time and depth information, and is configured with parameters to determine the starting point for data reading; The data parsing and preprocessing module is used to parse the original data file to identify the starting position of valid data, convert the data into standard time series format and numerical depth data, and obtain the converted time data and depth data. The instantaneous velocity calculation module is used to calculate the corresponding instantaneous settlement velocity data based on the converted time data and depth data; An adaptive segmentation and feature extraction module is used to automatically segment independent settlement process data segments from continuous depth data; It monitors depth data and marks the starting point when the depth continuously exceeds a first preset threshold; then it tracks depth changes until the maximum depth point is identified. Subsequently, when the depth falls back to a point where the difference between the depth at the starting point and the depth at the starting point is less than a second preset threshold, it is marked as the end point, thereby extracting a complete settlement process; The hierarchical statistics and visualization module is used to perform velocity statistics on the settlement process data segment according to at least one preset depth interval and generate charts. It performs settlement velocity statistics according to preset depth ranges and generates a dual-axis chart that simultaneously displays depth and velocity curves on the horizontal axis at the same time, thereby achieving data visualization.

2. The intelligent identification and processing system for sedimentation process data of depth gauges according to claim 1, characterized in that: The data input and configuration module includes: The file path acquisition unit is used to receive the input raw data file from the depth sensor; The parameter setting unit, connected to the file path acquisition unit, is used to allow users to manually set the number of lines to skip or select an automatic recognition mode to determine the starting point for data reading.

3. The intelligent identification and processing system for sedimentation process data of depth gauges according to claim 1, characterized in that: The data parsing and preprocessing module includes: A multi-encoding attempt unit is used to attempt to read the original data file in multiple character encoding formats; The header intelligent positioning unit, connected to the multi-encoding attempt unit, is used to determine the starting position of a valid data row by traversing the contents of the first predetermined number of rows of the original data file and identifying the row number where the predetermined keyword is located.

4. The intelligent identification and processing system for sedimentation process data of depth gauges according to claim 1, characterized in that: The instantaneous velocity calculation module includes: The differential calculation unit is used to calculate the ratio of the depth difference to the time difference between adjacent time points to obtain the original instantaneous velocity; The smoothing filter unit is used to perform noise reduction and smoothing processing on the original instantaneous velocity, and output stable velocity curve data.

5. The intelligent identification and processing system for sedimentation process data of depth gauges according to claim 1, characterized in that: The adaptive segmentation and feature extraction module includes: A threshold determination unit is used to monitor depth data. When the depth is continuously greater than a first preset threshold, the depth position is determined to be the starting point. The peak backtracking unit is used to track the maximum depth during a single deployment process, thereby determining the maximum depth point and locking the point where the depth data falls back to a depth less than the starting point depth, marking it as the end point. The validity verification unit is used to verify the segmented data segments, extract the data fragments from the start point to the end point, and if the maximum depth of the fragment is lower than the minimum effective depth threshold or the amount of data contained in the data segment is lower than the minimum quantity threshold, it is determined as invalid data and discarded; otherwise, it is marked as a valid data segment of the settlement process.

6. The intelligent identification and processing system for sedimentation process data of depth gauges according to claim 1, characterized in that: The adaptive segmentation and feature extraction module uses state machine logic to automatically segment independent settlement process data segments from the continuous depth data. The state machine includes: The waiting state is maintained when the depth data is less than the first preset threshold. The trigger state is entered when the depth data is continuously greater than or equal to the first preset threshold, and the time corresponding to the current data point is recorded as the starting point of the settlement process. Peak determination state, which is activated after entering the trigger state, is used to continuously analyze depth data to identify local maximum values ​​or determine whether the depth exceeds the large depth threshold, thereby determining the maximum depth point; The judgment state ends after the maximum depth point is identified. This state is used to record the current point as the end point when the depth data falls back to a depth less than the second preset threshold.

7. The intelligent identification and processing system for sedimentation process data of depth gauges according to claim 1, characterized in that: The hierarchical statistics and visualization module includes: Boolean mask statistics unit, used to calculate and statistically analyze the average velocity over a preset depth range; A dual-axis drawing engine unit is used to generate a coordinate system with a shared time axis, the coordinate system including a first vertical axis for representing depth values ​​and a second vertical axis for representing velocity values, and outputs the data according to a preset style.

8. The intelligent identification and processing system for sedimentation process data of depth gauges according to claim 7, characterized in that: The statistical operations performed by the Boolean mask statistical unit are equal-segment statistics and / or fixed-depth statistics; The equal division statistics are used to divide a complete settlement process data segment into M segments in chronological order, and calculate the average velocity in each segment, where M is an integer greater than 1. The fixed-depth statistics are used to calculate the average velocity and sample size for each of the N pre-defined depth ranges, where N is an integer greater than 0. When performing the fixed-depth statistics, if the maximum depth of the settlement process data segment does not reach the predetermined depth range, the statistical results of the corresponding range will be marked as invalid or without data.

9. A method for intelligent identification and processing of sedimentation process data from a depth gauge, characterized in that, Includes the following steps: Step S1, Intelligent Data Reading and Head Recognition: Read the original data file, identify and extract valid time and depth data; Step S2, Data preprocessing and velocity calculation: The time data and depth data are standardized, the instantaneous settlement velocity is calculated based on the change of the depth data over time, and the instantaneous settlement velocity is smoothed. Step S3, Automatic Segmentation of Settlement Process: The continuous time series data is traversed, and the starting point, maximum depth point and ending point of the settlement process are identified through state machine logic, thereby extracting independent settlement process data segments; Step S4, velocity stratification analysis: For each data segment of the settlement process, perform velocity statistical analysis according to at least one preset depth interval; Step S5, Chart Generation and Output: Generate a dual-axis chart for each of the aforementioned settlement process data segments, simultaneously displaying the depth curve and velocity curve on the horizontal axis at the same time, and export the statistical results and charts.

10. The intelligent identification and processing method for sedimentation process data of depth gauges according to claim 9, characterized in that: In step S4, the velocity stratification analysis includes equal-part statistics and / or fixed-depth statistics; The equal division statistics are used to divide a complete settlement process data segment into M segments in chronological order, and calculate the average velocity within each segment, where M is an integer greater than 1. The fixed-depth statistics are used to calculate the average velocity and sample size for each of the N pre-defined depth ranges, where N is an integer greater than 0. When performing the fixed-depth statistics, if the maximum depth of the settlement process data segment does not reach the predetermined depth range, the statistical results of the corresponding range will be marked as invalid or without data.

Images