Anesthesia equipment fault diagnosis method and system based on image recognition

Abstract

The invention discloses an anesthesia equipment fault diagnosis method and system based on image recognition, particularly relates to the technical field of medical equipment fault detection, and is used for solving the problem that a non-contact image detection method in existing anesthesia equipment pipeline leakage detection is poor in transparent pipeline weak leakage signal recognition capability. Through combination of multispectral dynamic imaging and polarized light scattering mode analysis, pipeline surface microscopic deformation characteristics are obtained, and a leakage path prediction result is generated. Environmental reflective noise is inhibited based on spectral distribution characteristics of the reference image set, optical response changes of the candidate area are triggered in combination with active pressure disturbance, and the inverse proportion physical relation between the permeation rate and the fluid conduction speed is verified; through dynamic threshold screening and spatial continuity verification, accurate positioning of a target area is realized, finally, spectral features, path forms and real-time pressure parameters are fused to generate leakage risk assessment, non-intrusive high-sensitivity leakage identification is realized, and reliable guarantee is provided for safe operation of clinical anesthesia equipment.

Description

Technical Field

[0001] The present invention relates to the technical field of medical equipment fault detection, and more specifically, to an anesthesia equipment fault diagnosis method and system based on image recognition. Background Art

[0002] During clinical use, anesthesia equipment must ensure the sealing and safety of the gas circuit system. Transparent pipes are prone to aging or micro-cracks due to long-term contact with gas and liquid, which may cause leakage risks. Currently, the detection of pipeline leakage mainly relies on contact monitoring methods such as pressure sensors and flow sensors. Such methods require direct connection to the equipment gas circuit, which has the problems of complex installation and high maintenance costs, and limited sensitivity to early trace leaks. In addition, some non-contact detection technologies analyze the equipment status through image acquisition, but they focus more on obvious fault characteristics such as deformation of mechanical parts or abnormal display values, and lack targeted processing of visual signals of leakage inside transparent pipes.

[0003] When dealing with transparent pipe leaks, existing detection methods based on image recognition are difficult to use to effectively distinguish between real leakage characteristics and noise because the optical signals of the liquid film or gas-liquid interface are weak in the early stage of leakage, and the optical interference (such as reflection and refraction) between the transparent material and the background environment is easy to cause confusion. This results in missed detections or misjudgments, making it impossible to identify early trace leaks in a timely manner, which may increase the risk of equipment failure and affect clinical safety. Summary of the invention

[0004] In order to overcome the above-mentioned defects of the prior art, the embodiments of the present invention provide an anesthesia equipment fault diagnosis method and system based on image recognition to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions: The anesthesia equipment fault diagnosis method based on image recognition includes the following steps: S1, obtaining a reference image set and a dynamic image set of a transparent pipeline area of ​​an anesthesia device; S2, based on the change of polarized light scattering pattern on the transparent pipe surface in the dynamic image set, the micro deformation area is identified, and the potential leakage path prediction result is generated in combination with the fluid conduction direction; S3, based on the pixel distribution characteristics of the reference image set and the potential leakage path prediction results, suppress the ambient reflection noise in the non-leakage path area, and extract the candidate area within the leakage path range and with a spectral difference from the noise; S4. Active pressure disturbance triggers the change of spectral reflectance in the candidate area, and verifies the inverse relationship between the permeation rate and the conduction velocity in combination with the fluid conduction velocity, thus screening the suspected fault area; S5. Determine the spectral intensity fluctuation threshold of the suspected fault area, and select the target area where the spectral intensity fluctuation exceeds the spectral intensity fluctuation threshold and overlaps with the microscopic deformation area space; S6. Match the spectral reflectance variation characteristics of the target area and the spatial distribution pattern of the potential leakage path prediction results to generate leakage risk assessment results.

[0006] In a preferred embodiment, obtaining a reference image set and a dynamic image set of a transparent pipeline area of ​​an anesthesia device includes: Multispectral imaging equipment is used to collect a reference image set containing visible light bands and near-infrared bands when the transparent pipeline is leak-free. The filter band covers the characteristic absorption peak of the pipeline material under normal sealing conditions. During the operation of the anesthesia equipment, a dynamic image set containing the polarized light scattering characteristics of the pipeline surface is synchronously acquired, and the real-time pressure parameters inside the pipeline are synchronously recorded during each acquisition; The polarization filter angle is adjusted to obtain a dynamic image set with the same filter band and polarization angle as the reference image set.

[0007] In a preferred embodiment, based on the change of polarized light scattering pattern on the surface of the transparent pipe in the dynamic image set, the microscopic deformation area is identified, and the potential leakage path prediction result is generated in combination with the fluid conduction direction, including: Extract the scattered images at different polarization angles in the dynamic image set, and calculate the gray value difference of the same area on the pipeline surface at each polarization angle; Areas based on grayscale value differences exceeding the grayscale fluctuation range of the reference image set at the same polarization angle are marked as micro-deformation areas; Combining the fluid conduction direction in the gas circuit of the anesthesia equipment with the spatial distribution of the microscopic deformation area, the boundary of the microscopic deformation area is extended along the fluid conduction direction to generate a potential leakage path; The potential leakage paths whose matching degree with the normal deformation pattern of the pipeline in the reference image set is higher than the preset threshold are eliminated, and the prediction results of the potential leakage paths are retained.

[0008] In a preferred embodiment, according to the pixel distribution characteristics of the reference image set and the potential leakage path prediction results, the ambient reflection noise in the non-leakage path area is suppressed, and the candidate area within the leakage path range and having a spectral difference with the noise is extracted, including: A noise mask is generated based on the pixel grayscale distribution in the filter band of the reference image set, where the noise mask covers the environmental reflection area in the dynamic image set and the area outside the potential leakage path prediction result; Compare the spectral difference values ​​of the dynamic image set and the reference image set in the same filter band, and select the area within the leakage path where the spectral difference value exceeds the upper limit of the grayscale distribution of the noise mask as the initial candidate area; Dynamically adjust the noise suppression threshold according to the real-time pressure parameter fluctuation direction; Verify the spatial overlap ratio between the initial candidate region and the microscopic deformation region, eliminate candidate regions whose spatial overlap ratio is lower than the preset value, and retain candidate regions that meet the spatial overlap ratio and whose spectral difference values ​​meet the dynamic threshold.

[0009] In a preferred embodiment, if the pressure fluctuation amplitude increases, the noise suppression threshold is lowered, and if the pressure fluctuation amplitude decreases, the noise suppression threshold is increased.

[0010] In a preferred embodiment, the active pressure disturbance triggers the change of the spectral reflectance of the candidate area, and the inverse relationship between the permeation rate and the conduction velocity is verified in combination with the fluid conduction velocity to screen the suspected fault area, including: Apply a pressure disturbance of a preset duration to the candidate area, and simultaneously record the change amplitude of the spectral reflectance of the candidate area in the same filter band before and after the pressure disturbance; The theoretical permeation rate threshold is calculated based on the fluid conductivity velocity, which is derived from Poiseuille's law based on the real-time pressure difference and the inner diameter of the pipeline; The candidate areas whose spectral reflectance variation amplitude is inversely proportional to the theoretical penetration rate threshold are selected as suspected fault areas; Eliminate interference areas in the candidate area where the direction of spectral reflectance change is inconsistent with the direction of pressure disturbance.

[0011] In a preferred embodiment, the inverse relationship is verified to satisfy the requirement that the amplitude of the spectral reflectance change is less than 1 / N times of the theoretical permeability threshold, where N is the linear coefficient of the fluid conductivity.

[0012] In a preferred embodiment, determining a spectral intensity fluctuation threshold of a suspected fault area, and screening a target area whose spectral intensity fluctuation exceeds the spectral intensity fluctuation threshold and overlaps with the microscopic deformation area space, comprises: Perform time series analysis on the spectral reflectance changes in the suspected fault area, and calculate the standard deviation of the fluctuation amplitude within the preset time window as the spectral intensity fluctuation threshold; Dynamically correct the spectral intensity fluctuation threshold based on the historical spectral fluctuation data of the normal deformation area in the reference image set, and the correction amplitude is positively correlated with the real-time pressure parameter fluctuation amplitude; The candidate regions whose spectral intensity fluctuation values ​​exceed the corrected spectral intensity fluctuation threshold and whose spatial overlap rate with the microscopic deformation region is higher than the preset overlap threshold are selected as target regions; Verify the consistency between the spectral fluctuation direction and the pressure disturbance direction of the target area, and eliminate candidate areas with reverse fluctuation directions.

[0013] In a preferred embodiment, matching the spectral reflectance variation characteristics of the target area and the spatial distribution form of the potential leakage path prediction results to generate leakage risk assessment results includes: Extract the spectral reflectance change characteristics of the target area, and match the spectral reflectance change characteristics with the spatial distribution form of the potential leakage path prediction results. The matching of the spatial distribution form includes the path direction, extension length and the overlap ratio with the micro deformation area; Verify the negative correlation between the rate of change of the spectral reflectance of the target area and the fluid conduction velocity in the leakage path, and select the target area that meets the rate-velocity negative correlation; Analyze the spatial continuity of the target area on the leakage path and eliminate the isolated areas that do not meet the consistency of the path conduction direction; Based on the real-time pressure parameters, dynamic weight allocation is performed on the spectral reflectance variation amplitude and spatial continuity to generate a comprehensive leakage risk assessment result.

[0014] On the other hand, the present invention provides an anesthesia equipment fault diagnosis system based on image recognition, comprising: Image acquisition module: obtains the reference image set and dynamic image set of the transparent pipeline area of ​​the anesthesia equipment; Polarization path module: identifies microscopic deformation areas based on the changes in polarized light scattering patterns on the surface of transparent pipes in dynamic image sets, and generates potential leakage path prediction results based on the fluid conduction direction; Noise reduction and extraction module: Based on the pixel distribution characteristics of the reference image set and the potential leakage path prediction results, the ambient reflection noise in the non-leakage path area is suppressed, and the candidate area within the leakage path range with spectral differences from the noise is extracted; Disturbance verification module: Active pressure disturbance triggers the change of spectral reflectance in the candidate area, and verifies the inverse relationship between penetration rate and conduction velocity in combination with fluid conduction velocity, thus screening suspected fault areas; Threshold screening module: determines the spectral intensity fluctuation threshold of the suspected fault area, and screens the target area whose spectral intensity fluctuation exceeds the spectral intensity fluctuation threshold and overlaps with the microscopic deformation area space; Assessment generation module: Matches the spectral reflectance variation characteristics of the target area and the spatial distribution of the potential leakage path prediction results to generate leakage risk assessment results.

[0015] Compared with the prior art, the present invention has the following beneficial effects: 1. Through the deep integration of multimodal optical features and fluid conduction characteristics, high-sensitivity and high-specificity detection of early leakage in transparent pipelines is achieved. Based on the collaborative analysis of polarized light scattering patterns and multi-spectral dynamic imaging, it can effectively capture microscopic deformation and liquid film diffusion characteristics that are difficult to identify with traditional visual methods. Through the closed-loop logic of leakage path prediction and noise suppression, the misjudgment caused by ambient light interference is significantly reduced. The active pressure perturbation design is combined with the inverse relationship verification of the permeation rate to dynamically bind the optical response with the fluid mechanics parameters, making the weak leakage signal explicit under the constraints of physical laws, solving the problem of missed detection caused by traditional image detection relying on static thresholds, and avoiding the interference of contact sensors on the operation status of the equipment, providing a non-invasive and highly reliable leakage monitoring method for clinical scenarios; 2. Through the dual screening mechanism of spectral intensity fluctuation threshold and spatial overlap verification, the accurate positioning of real leakage characteristics is achieved. Its dynamic weight allocation and path continuity evaluation strategy can adapt to pressure fluctuations and fluid state changes under different working conditions to ensure the high consistency between risk assessment results and physical characteristics of leakage. Through cross-dimensional data fusion (optical, spatial, fluid conduction) and multi-stage logic verification, it breaks through the limitations of a single detection dimension in a complex interference environment, improves the detection rate of early trace leaks, and avoids false alarms caused by local noise or instantaneous disturbances, providing full-link closed-loop support from feature recognition to risk decision-making for the safety maintenance of anesthesia equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 It is a flow chart of the anesthesia equipment fault diagnosis method based on image recognition of the present invention; Figure 2 The figure is a schematic diagram of the structure of the anesthesia equipment fault diagnosis system based on image recognition of the present invention. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0018] Embodiment 1: Figure 1 The present invention provides an anesthesia equipment fault diagnosis method based on image recognition, which comprises the following steps: S1, obtaining a reference image set and a dynamic image set of a transparent pipeline area of ​​an anesthesia device; S2, based on the change of polarized light scattering pattern on the transparent pipe surface in the dynamic image set, the micro deformation area is identified, and the potential leakage path prediction result is generated in combination with the fluid conduction direction; S3, based on the pixel distribution characteristics of the reference image set and the potential leakage path prediction results, suppress the ambient reflection noise in the non-leakage path area, and extract the candidate area within the leakage path range and with a spectral difference from the noise; S4. Active pressure disturbance triggers the change of spectral reflectance in the candidate area, and verifies the inverse relationship between the permeation rate and the conduction velocity in combination with the fluid conduction velocity, thus screening the suspected fault area; S5. Determine the spectral intensity fluctuation threshold of the suspected fault area, and select the target area where the spectral intensity fluctuation exceeds the spectral intensity fluctuation threshold and overlaps with the microscopic deformation area space; S6. Match the spectral reflectance variation characteristics of the target area and the spatial distribution pattern of the potential leakage path prediction results to generate leakage risk assessment results. S1. Obtain a baseline image set and a dynamic image set of the transparent pipeline area of ​​the anesthesia equipment, including: Multispectral imaging equipment is used to collect a reference image set containing visible light bands and near-infrared bands when the transparent pipeline is leak-free. The filter band covers the characteristic absorption peak of the pipeline material under normal sealing conditions. During the operation of the anesthesia equipment, a dynamic image set containing the polarized light scattering characteristics of the pipeline surface is synchronously acquired, and the real-time pressure parameters inside the pipeline are synchronously recorded during each acquisition; The polarization filter angle is adjusted to obtain a dynamic image set with the same filter band and polarization angle as the reference image set.

[0019] The filter band of the multi-spectral imaging device covers the characteristic absorption peak of the transparent pipe material in the normal sealing state. For example, the central wavelength of the filter band includes 515 nanometers and 550 nanometers in the visible light band and 830 nanometers and 905 nanometers in the near infrared band, and the bandwidth of each filter band is 10 nanometers to 20 nanometers.

[0020] The characteristic absorption peak is determined by pre-testing the transparent pipe material with Fourier transform infrared spectroscopy. During the specific test, the transparent pipe material is cut into thin slices with a thickness of 1 mm and placed in the sample chamber of the Fourier transform infrared spectrometer. The scanning wavelength range is 400 nanometers to 2500 nanometers to identify the position of the characteristic absorption peak of the material in a normal sealing state, and the center wavelength of the filter band of the multi-spectral imaging equipment is set to be consistent with the position of the characteristic absorption peak.

[0021] For example, when the material has a characteristic absorption peak at 830 nanometers in the near-infrared band, the central wavelength of the filter band is set to 830 nanometers. The acquisition frequency of the benchmark image set is 5 frames per second, the exposure time of each frame is 20 milliseconds, and the ambient light intensity is controlled between 300 lux and 500 lux, for example, by adjusting the brightness of the operating room light. During acquisition, the distance between the multispectral imaging device and the transparent pipe is fixed at 30 cm, and the optical axis of the imaging device is perpendicular to the surface of the pipe.

[0022] The dynamic image set uses the same multispectral imaging equipment as the reference image set, and records the internal pressure parameters of the pipeline in real time through the pressure sensor during each acquisition. For example, the sampling frequency of the pressure sensor is consistent with the image acquisition frequency, and the pressure data is aligned with the timestamp of the dynamic image set. The polarization angles of the dynamic image set include 0 degrees, 45 degrees and 90 degrees. In specific implementation, the capture of light in different polarization directions is achieved by rotating the angle of the polarization filter. For example, the rotation of the polarization filter is driven by a stepper motor with a rotation accuracy of ±1 degree. After each switching of the polarization angle, wait for 100 milliseconds to ensure that the filter is stable before starting image acquisition. The filter band of the dynamic image set is consistent with the reference image set, for example, the filter band is set at 515 nanometers in the visible light band.

[0023] The exposure time of the dynamic image set is dynamically adjusted according to the ambient light intensity. For example, when the ambient light intensity is lower than 300 lux, the exposure time is increased to 30 milliseconds, and when it is higher than 500 lux, it is reduced to 10 milliseconds to ensure consistent image brightness.

[0024] When adjusting the polarization filter angle, calibration is performed based on the polarization angle parameters of the reference image set. For example, the calibration process includes collecting a set of calibration images in a no-leakage state, and adjusting the polarization filter angle until the error between the polarized light scattering pattern of the calibration image and the scattering pattern of the reference image set at the same polarization angle is less than 5%.

[0025] The error calculation uses the root mean square error of the pixel grayscale value. For example, a 100×100 pixel block in the same area of ​​the pipeline surface is selected to compare the grayscale value difference between the calibration image and the reference image in this block. If the root mean square error exceeds 5%, the polarization filter angle is fine-tuned until it meets the standard, for example, by fine-tuning the stepper motor by 0.5 degrees, then re-acquire the calibration image and calculate the error. After the calibration is completed, the filter position is locked and the dynamic image set is collected.

[0026] The pressure parameters are obtained through a piezoresistive pressure sensor installed at the outlet of the anesthesia equipment. For example, the sensor range is -10 kPa to 100 kPa, with an accuracy of ±0.5% full scale, and the pressure data and the timestamp of the dynamic image are synchronized through the same clock source. For example, the clock source uses the internal crystal oscillator of the embedded system, with a frequency stability of ±50ppm and a timestamp accuracy of 1 millisecond, ensuring the accurate correspondence between the pressure data and the image frame.

[0027] Through the steps, the optical conditions of the reference image set and the dynamic image set are consistent, including the filter band, polarization angle, ambient light intensity and imaging distance, thus providing a comparable data basis for noise suppression and feature extraction in the subsequent steps. For example, the consistency of the filter band makes the spectral difference analysis in the subsequent steps comparable, the consistency of the polarization angle ensures that the change of the scattering pattern is only caused by the pipeline status, and the dynamic adjustment of the ambient light intensity avoids external light interference.

[0028] S2. Identify microscopic deformation areas based on the changes in polarized light scattering patterns on the surface of transparent pipes in dynamic image sets, and generate potential leakage path prediction results based on the fluid conduction direction, including: Extract the scattered images at different polarization angles in the dynamic image set, and calculate the gray value difference of the same area on the pipeline surface at each polarization angle; Areas based on grayscale value differences exceeding the grayscale fluctuation range of the reference image set at the same polarization angle are marked as micro-deformation areas; Combining the fluid conduction direction in the gas circuit of the anesthesia equipment with the spatial distribution of the microscopic deformation area, the boundary of the microscopic deformation area is extended along the fluid conduction direction to generate a potential leakage path; The potential leakage paths whose matching degree with the normal deformation pattern of the pipeline in the reference image set is higher than the preset threshold are eliminated, and the prediction results of the potential leakage paths are retained.

[0029] When extracting scattering images at different polarization angles in the dynamic image set, a multispectral imaging device is used to obtain scattering images at polarization angles of 0, 45 and 90 degrees. The filter band of the multispectral imaging device is consistent with the reference image set, such as 515 nanometers in the visible light band and 830 nanometers in the near infrared band. The image acquisition interval for each polarization angle is 200 milliseconds to ensure that the changes in the state of the pipeline surface are fully recorded. When calculating the gray value difference of the same area on the pipeline surface at each polarization angle, a 100×100 pixel area with fixed coordinates on the pipeline surface is selected, and the average gray value of the area in the polarization angle images of 0, 45 and 90 degrees is calculated respectively. The gray value of the 0-degree polarization image is used as a reference to calculate the gray difference value of the corresponding area of ​​the 45-degree and 90-degree images. For example, when the gray value of the 45-degree image is 15 to 20 units lower than that of the 0-degree image, it is determined that there is a change in the scattering pattern.

[0030] When marking the micro deformation area based on the area whose grayscale value difference exceeds the grayscale fluctuation range of the benchmark image set at the same polarization angle, the grayscale fluctuation range of the benchmark image set is determined by statistically analyzing the standard deviation of the grayscale values ​​of the same pipeline area in multiple acquisitions under a no-leakage state. For example, the standard deviation is ±5 at a polarization angle of 0 degrees. When the grayscale difference value of a certain area in the dynamic image exceeds 3 times the benchmark standard deviation, it is marked as a micro deformation area. The boundary of the deformation area is determined by connected domain analysis, and the areas where the grayscale difference of adjacent pixels exceeds the threshold are merged into the same deformation area.

[0031] When generating a potential leakage path by combining the fluid conduction direction in the air circuit of the anesthesia equipment with the spatial distribution of the microscopic deformation area, the fluid conduction direction is calculated based on the pressure difference between the inlet and outlet of the air circuit of the anesthesia equipment. For example, when the inlet pressure is 40 kPa and the outlet pressure is 35 kPa, the fluid conduction direction is from the inlet to the outlet. The boundary of the microscopic deformation area is extended toward the downstream of the fluid along this direction. The extension step is 0.5 times the diameter of the pipeline. For example, when the pipeline diameter is 10 mm, the extension step is 5 mm. The number of extensions is dynamically adjusted according to the fluid velocity. The fluid velocity is calculated through the pressure difference and the inner diameter of the pipeline. For example, when the pressure difference is 5 kPa and the inner diameter is 10 mm, the fluid velocity is 0.2 meters per second. The boundary is extended once per second to generate a continuously extended potential leakage path.

[0032] When eliminating potential leakage paths whose matching degree with the normal deformation pattern of the pipeline in the reference image set is higher than the preset threshold, the normal deformation pattern is determined by statistically analyzing the shape parameters of all deformation areas in the reference image set. The shape parameters include the aspect ratio, area and perimeter of the area. For example, the average aspect ratio of the normal deformation area is 1.2, and the average area is 50 square pixels. The deformation area corresponding to the potential leakage path is calculated for similarity with the normal deformation pattern. The similarity calculation adopts the weighted sum of the aspect ratio and the area, with weights of 0.6 and 0.4 respectively. When the weighted similarity exceeds the preset threshold of 90%, it is judged as a normal deformation and eliminated, and the abnormal leakage path with a weighted similarity lower than 90% is retained as the prediction result.

[0033] The weight allocation of aspect ratio and area is determined based on the contribution of the two types of parameters to the leakage judgment in the historical leakage data. For example, through the statistics of historical leakage cases, it is found that the aspect ratio contributes about 60% to the discrimination of abnormal leakage, and the area contributes about 40%, so the weights are set to 0.6 and 0.4. The weight allocation process includes: performing a logistic regression analysis on the aspect ratio and area of ​​all deformed areas in the historical leakage data, calculating the regression coefficient ratio of the two types of parameters, and normalizing the ratio to a weight.

[0034] The preset threshold is determined through experimental verification, which specifically includes: collecting multiple sets of normal deformation data in a non-leakage state, calculating the similarity distribution between the normal deformation area and the benchmark data, and taking the upper limit of the similarity distribution as the threshold. For example, if the highest similarity of the normal deformation area is 89%, the threshold is set to 90% to cover the normal fluctuation range.

[0035] When obtaining the similarity distribution between the normal deformation area and the benchmark data, the specific method is as follows: in a no-leakage state, multiple groups of normal deformation image data are collected, and the contours and characteristic parameters of each deformation area on the pipeline surface are extracted through image segmentation; the geometric structure, texture distribution and edge features of each deformation area are matched region by region with the standardized data of the corresponding position in the benchmark database, and the feature weighted fusion algorithm is used to calculate the overall similarity between each area and the benchmark data; the similarity calculation results of all normal samples are statistically analyzed, and the similarity probability distribution curve is drawn to determine its concentration interval and discrete boundary, and finally the similarity distribution result covering the normal deformation fluctuation range is obtained, for example, the upper limit threshold of the distribution is determined by normal distribution fitting or non-parametric statistical methods.

[0036] The retained potential leakage path prediction results are stored in the form of a coordinate point sequence. Each coordinate point corresponds to the position on the pipeline surface. The sequence direction is consistent with the fluid conduction direction. The path length is calculated based on the fluid velocity and the number of extensions. For example, when the fluid velocity is 0.2 meters per second and the number of extensions is 10, the path length is 2 meters. Finally, a leakage prediction report including path coordinates, length and risk level is generated.

[0037] S3. According to the pixel distribution characteristics of the reference image set and the potential leakage path prediction results, the ambient reflection noise in the non-leakage path area is suppressed, and the candidate area within the leakage path range and with spectral differences from the noise is extracted, including: A noise mask is generated based on the pixel grayscale distribution in the filter band of the reference image set, where the noise mask covers the environmental reflection area in the dynamic image set and the area outside the potential leakage path prediction result; Compare the spectral difference values ​​of the dynamic image set and the reference image set in the same filter band, and select the area within the leakage path where the spectral difference value exceeds the upper limit of the grayscale distribution of the noise mask as the initial candidate area; Dynamically adjust the noise suppression threshold according to the real-time pressure parameter fluctuation direction. If the pressure fluctuation amplitude increases, the noise suppression threshold is lowered; if the pressure fluctuation amplitude decreases, the noise suppression threshold is increased. Verify the spatial overlap ratio between the initial candidate region and the microscopic deformation region, eliminate candidate regions whose spatial overlap ratio is lower than the preset value, and retain candidate regions that meet the spatial overlap ratio and whose spectral difference values ​​meet the dynamic threshold.

[0038] When generating the noise mask, the filter band of the reference image set is consistent with that of the dynamic image set, such as 515 nanometers for the visible light band and 830 nanometers for the near infrared band. The reference image set collects multiple sets of images in a non-leak state, and the pixel grayscale distribution of each area on the pipeline surface under the same filter band is counted. The grayscale distribution is determined by calculating the grayscale value range of each area in multiple acquisitions. For example, under the 515 nanometer filter band, the grayscale value of a certain area fluctuates between 120 and 150, with a range of 30. The noise mask covers the areas in the dynamic image set whose grayscale values ​​are within the range and are outside the potential leakage path prediction results. For example, if the grayscale value of a certain area in the dynamic image is 140 and is outside the leakage path range, it is marked as an environmental reflection noise area. When screening areas within the leakage path range where the spectral difference value exceeds the upper limit of the grayscale distribution of the noise mask, the dynamic image set and the reference image set are compared at the same filter band at the pixel level. For example, at the 830-nanometer filter band, the grayscale value of a pixel in the dynamic image is 25 lower than that of the reference image. The upper limit of the grayscale distribution of the noise mask is determined by counting the 95% quantile of the grayscale value of the reference image set at the same filter band. For example, the upper limit is 160. When the dynamic pixel grayscale difference value exceeds 25 and is within the leakage path range, it is marked as an initial candidate area.

[0039] When the noise suppression threshold is dynamically adjusted according to the real-time pressure parameter fluctuation direction, the pressure fluctuation amplitude is determined by calculating the pressure difference between adjacent time points. For example, if the current pressure is 40 kPa and the previous time point is 38 kPa, the fluctuation amplitude is increased by 2 kPa. If the pressure fluctuation amplitude increases, it indicates that the fluid state in the pipeline is unstable and may be accompanied by leakage risks. At this time, the noise suppression threshold is lowered to capture weaker spectral difference signals, for example, the threshold is adjusted from 25 to 20. If the pressure fluctuation amplitude decreases, it indicates that the fluid state tends to be stable. At this time, the noise suppression threshold is increased to reduce false detections, for example, the threshold is adjusted from 25 to 30. The adjusted dynamic threshold is used to screen the spectral difference values ​​of the initial candidate areas. For example, when the pressure fluctuation amplitude increases, only candidate areas with grayscale difference values ​​exceeding 20 are retained.

[0040] When verifying the spatial overlap ratio between the initial candidate area and the micro deformation area, the spatial overlap ratio is determined by calculating the percentage of overlapping pixels between the candidate area and the micro deformation area. For example, if the candidate area contains 100 pixels, of which 60 pixels overlap with the micro deformation area, the overlap ratio is 60%. The preset value is set according to the overlap ratio statistics of the normal deformation area in the reference image set. For example, the average overlap ratio of the normal deformation area in the non-leakage state is 55%, and the preset value is set to 50%. When the overlap ratio of the candidate area is lower than 50%, it is determined to be noise interference and eliminated. Candidate areas whose overlap ratio meets the standard and whose spectral difference values ​​meet the dynamic threshold are retained. For example, if the overlap ratio of a candidate area is 55%, the spectral difference value is 22 and the dynamic threshold is 20, it is retained. The coordinates of the retained candidate areas are matched with the spatial distribution morphology of the leakage path prediction results. For example, if the candidate area is located in the extension direction of the leakage path and is continuously adjacent to the path coordinate sequence, it is determined to be a valid leakage feature area.

[0041] The noise suppression and candidate region extraction process combines the consistency of the filter band, the spatial constraint of the leakage path, the dynamic threshold of the pressure parameter and the overlap verification of the deformation area to ensure the high sensitivity capture of the weak leakage signal of the transparent pipe, while eliminating the interference of environmental reflection and normal deformation. For example, under the 515-nanometer filter band, after the initial candidate area is screened by the dynamic threshold and overlapped, the spectral difference value of the final retained area is between 20 and 30, and the overlap ratio with the microscopic deformation area exceeds 50%, thus providing reliable input for subsequent leakage risk assessment.

[0042] S4. Active pressure disturbance triggers the change of spectral reflectance in the candidate area, and verifies the inverse relationship between the permeation rate and the conduction velocity in combination with the fluid conduction velocity, and screens the suspected fault area, including: Apply a pressure disturbance of a preset duration to the candidate area, and simultaneously record the change amplitude of the spectral reflectance of the candidate area in the same filter band before and after the pressure disturbance; The theoretical permeation rate threshold is calculated based on the fluid conductivity velocity, which is derived from Poiseuille's law based on the real-time pressure difference and the inner diameter of the pipeline; The candidate areas whose spectral reflectance variation amplitude is inversely proportional to the theoretical permeability threshold are selected as suspected fault areas; the inverse relationship verification satisfies that the spectral reflectance variation amplitude is less than 1 / N times of the theoretical permeability threshold, where N is the linear coefficient of the fluid conduction velocity; Eliminate interference areas in the candidate area where the direction of spectral reflectance change is inconsistent with the direction of pressure disturbance.

[0043] When a preset pressure disturbance is applied to the candidate area, the pressure inside the pipeline is adjusted for a short time through the gas circuit control system of the anesthesia equipment, for example, the pressure is increased from 40 kPa to 45 kPa within 1 second and maintained for 2 seconds before returning to the original pressure, and the spectral reflectance data of the candidate area in the same filter band before and after the pressure disturbance are collected simultaneously. The amplitude of the change in spectral reflectance is determined by calculating the difference in the average grayscale value of the same candidate area before and after the pressure disturbance. For example, the average grayscale value of the candidate area in the 515 nm filter band before the disturbance is 120, and it drops to 100 after the disturbance, so the amplitude of the change is 20 units. The filter band is consistent with the reference image set, such as 515 nm in the visible light band and 830 nm in the near infrared band, to ensure the comparability of spectral data.

[0044] When calculating the theoretical permeation rate threshold value based on the fluid conduction velocity, the fluid conduction velocity is derived from the Poiseuille law based on the real-time pressure difference and the inner diameter of the pipeline, specifically including: calculating the flow rate based on the real-time pressure difference between the inlet and outlet of the anesthesia equipment gas circuit, for example, when the inlet pressure is 45 kPa and the outlet pressure is 40 kPa, the pressure difference is 5 kPa, combined with the inner diameter of the pipeline of 10 mm, the fluid conduction velocity is calculated by the Poiseuille law to be 0.25 meters per second. The theoretical permeation rate threshold is inversely proportional to the fluid conduction velocity. For example, when the conduction velocity is 0.25 meters per second, the theoretical permeation rate threshold is set to 0.05 milliliters per second, and when the conduction velocity is increased to 0.5 meters per second, the threshold is reduced to 0.025 milliliters per second. The threshold calculation is based on the physical law that the permeation rate of the leaked substance in the pipeline decreases with the increase of the flow velocity. For example, the faster the flow velocity, the shorter the residence time of the leaked substance on the pipeline surface and the less the permeation amount.

[0045] When screening candidate areas where the amplitude of the spectral reflectance change is inversely proportional to the theoretical permeability threshold, the inverse relationship verification must satisfy the requirement that the amplitude of the spectral reflectance change is less than 1 / N times the theoretical permeability threshold, where N is the linear coefficient of the fluid conduction velocity. For example, when the fluid conduction velocity is 0.25 meters per second, N is set to 5, and the theoretical permeability threshold is 0.05 milliliters per second, then the amplitude of the spectral reflectance change must be less than 0.01 milliliters equivalent (0.05 / 5). If the amplitude of the candidate area change is 0.008 milliliters equivalent, it is determined to meet the inverse relationship. The linear coefficient N is determined by experimental calibration. For example, the amplitude of the reflectance change corresponding to different flow rates is measured under a known leakage rate, and the linear relationship between the N value and the flow rate is fitted as N=flow rate×pipeline length. When the pipeline length is 2 meters, a flow rate of 0.25 meters per second corresponds to N=0.5.

[0046] When excluding the interference area in the candidate area where the direction of spectral reflectivity change is inconsistent with the direction of pressure disturbance, the correlation between the direction of pressure disturbance and the direction of spectral reflectivity change is verified by physical laws. For example, when a positive pressure disturbance (pressurization) is applied, the thickness of the liquid film in the leakage area becomes thinner due to the increase in pressure, resulting in a decrease in spectral reflectivity. If the reflectivity of the candidate area increases after pressurization, it is judged as interference; conversely, in the case of negative pressure disturbance (depressurization), the reflectivity should increase, and if it decreases, it is eliminated. During verification, the corresponding relationship between the direction of pressure disturbance and the direction of reflectivity change is recorded. For example, if the reflectivity decreases by more than 5 units after pressurization, it is a valid signal, and the candidate area with a change amplitude less than 5 or in the opposite direction is excluded. The retained suspected fault area must meet both the inverse relationship verification and direction consistency. For example, if the reflectivity of a candidate area decreases by 18 units after pressurization, the corresponding permeation rate equivalent is 0.009 ml, which is less than the theoretical threshold of 0.01 ml, and the change direction is in line with expectations, it is marked as a suspected fault area.

[0047] The spectral reflectivity change characteristics of the candidate area are bound to the physical laws of fluid conduction velocity, and combined with the verification of the pressure disturbance direction, it can effectively distinguish between real leakage signals and random noise. For example, under the 830-nanometer filter band, the spectral reflectivity change amplitude of a candidate area is 15 units, corresponding to a permeation rate equivalent of 0.007 ml, which is less than the theoretical threshold of 0.01 ml, and the reflectivity decreases in the same direction after pressurization, then it is determined to be a suspected fault area and enter the subsequent steps for processing.

[0048] S5. Determine the spectral intensity fluctuation threshold of the suspected fault area, and screen the target area whose spectral intensity fluctuation exceeds the spectral intensity fluctuation threshold and overlaps with the microscopic deformation area space, including: Perform time series analysis on the spectral reflectance changes in the suspected fault area, and calculate the standard deviation of the fluctuation amplitude within the preset time window as the spectral intensity fluctuation threshold; Dynamically correct the spectral intensity fluctuation threshold based on the historical spectral fluctuation data of the normal deformation area in the reference image set, and the correction amplitude is positively correlated with the real-time pressure parameter fluctuation amplitude; The candidate regions whose spectral intensity fluctuation values ​​exceed the corrected spectral intensity fluctuation threshold and whose spatial overlap rate with the microscopic deformation region is higher than the preset overlap threshold are selected as target regions; Verify the consistency between the spectral fluctuation direction and the pressure disturbance direction of the target area, and eliminate candidate areas with reverse fluctuation directions.

[0049] When performing time series analysis on the spectral reflectance changes of suspected faulty areas, the preset time window is set according to the typical leakage response time of the anesthesia equipment, for example, the time window is 5 seconds, and the spectral reflectance data of the candidate area within this time period is continuously collected. The standard deviation of the spectral reflectance change amplitude is determined by calculating the average grayscale value fluctuation of each frame image within the time window. For example, the average grayscale value of a candidate area fluctuates from 120 to 110 within 5 seconds, and the standard deviation is 8.5. The spectral intensity fluctuation threshold is set to 1.5 times the standard deviation, that is, 12.75. Fluctuations exceeding this threshold are considered abnormal. The historical spectral fluctuation data of the normal deformation area in the reference image set is determined by statistically analyzing the standard deviation of the spectral reflectance of the same filter band in the non-leakage state. For example, the standard deviation mean of the normal deformation area in the 515 nanometer filter band is 5, and the fluctuation threshold reference value is 7.5.

[0050] When the spectral intensity fluctuation threshold is dynamically corrected based on the real-time pressure parameter fluctuation amplitude, the pressure fluctuation amplitude is determined by calculating the absolute value of the pressure difference at adjacent time points. For example, the current pressure is 42 kPa, the previous time point is 40 kPa, and the fluctuation amplitude is 2 kPa. The rule that the correction amplitude is positively correlated with the pressure fluctuation amplitude is: for every 1 kPa increase in pressure fluctuation, the fluctuation threshold is increased by 5%. For example, when the baseline threshold is 7.5, when the pressure fluctuation amplitude is 2 kPa, the corrected threshold is 7.5×(1+0.05×2)=8.25. If the pressure fluctuation amplitude is 5 kPa, the threshold is adjusted to 7.5×(1+0.05×5)=9.375. The threshold correction process is implemented by a table lookup method. The table stores correction coefficients corresponding to different pressure fluctuation amplitudes. For example, a pressure fluctuation of 1 kPa corresponds to a coefficient of 1.05, 2 kPa corresponds to 1.10, and so on.

[0051] When screening candidate areas whose spectral intensity fluctuation value exceeds the corrected threshold and whose spatial overlap rate with the micro deformation area is higher than the preset overlap threshold, the preset overlap threshold is set according to the average overlap ratio of the normal deformation area in the reference image set. For example, statistics show that the average overlap ratio between the normal deformation area and the micro deformation area is 55%, and the preset overlap threshold is set to 50%. For example, if the spectral intensity fluctuation value of a candidate area is 9.0, which exceeds the corrected threshold of 8.25, and the overlapping pixel ratio with the micro deformation area is 60%, which is higher than the preset value of 50%, it is marked as the target area. If the fluctuation value of the candidate area is 8.0 and the overlap ratio is 45%, it will be eliminated. The coordinate range of the target area and the boundary error of the micro deformation area are controlled within 10% of the pipeline diameter. For example, when the pipeline diameter is 10 mm, the allowable boundary error is ±1 mm.

[0052] When verifying the consistency between the spectral fluctuation direction of the target area and the pressure disturbance direction, the pressure disturbance direction is divided into two modes: pressurization and decompression. For example, in the pressurization stage (pressure increases from 40 kPa to 45 kPa), the spectral reflectivity of the normal leakage area should show a downward trend. If the reflectivity of the target area increases after pressurization, the direction is determined to be inconsistent and eliminated. Direction consistency verification is achieved by comparing the changes in spectral reflectivity of two frames of images before and after the pressure disturbance. For example, if the reflectivity drops by more than 5 units after pressurization, it is considered to be consistent in direction, and if it rises or drops by less than 5 units, it is eliminated. The target area after elimination must meet the three conditions of fluctuation threshold, spatial overlap rate and direction consistency. For example, if a certain area has a fluctuation value of 9.5 (threshold 8.25), an overlap rate of 60%, and a reflectivity drop of 6 units after pressurization, it will be retained as a valid target area.

[0053] The screening of target areas combines dynamic threshold correction, spatial overlap constraints and physical law verification. For example, in the 830-nanometer filter band, a candidate area has a fluctuation value of 9.8, an overlap rate of 65%, and a reflectivity drop of 7 units after pressurization. After meeting all conditions, it enters the final leakage risk assessment. During the screening process, interference signals with fluctuation values ​​below the threshold, insufficient overlap rates or abnormal directions are eliminated. For example, an area with a fluctuation value of 7.0 (threshold 8.25) is eliminated, and another area with a fluctuation value of 9.0 but a reflectivity increase of 3 units is also eliminated. The final retained target area list is transmitted to the subsequent steps to generate leakage risk assessment results.

[0054] S6. Match the spectral reflectance variation characteristics of the target area and the spatial distribution of the potential leakage path prediction results to generate leakage risk assessment results, including: Extract the spectral reflectance change characteristics of the target area, and match the spectral reflectance change characteristics with the spatial distribution form of the potential leakage path prediction results. The matching of the spatial distribution form includes the path direction, extension length and the overlap ratio with the micro deformation area; Verify the negative correlation between the rate of change of the spectral reflectance of the target area and the fluid conduction velocity in the leakage path, and select the target area that meets the rate-velocity negative correlation; Analyze the spatial continuity of the target area on the leakage path and eliminate the isolated areas that do not meet the consistency of the path conduction direction; Based on the real-time pressure parameters, dynamic weight allocation is performed on the spectral reflectance variation amplitude and spatial continuity to generate a comprehensive leakage risk assessment result.

[0055] When matching the spectral reflectance change characteristics of the target area with the spatial distribution form of the potential leakage path prediction results, the spectral reflectance change characteristics include the change amplitude, change rate and change direction. For example, after a pressure disturbance is applied to a certain target area, the spectral reflectance shows a continuous downward trend, while the reflectance of another area rises after the pressure is restored. Such dynamic change characteristics are used to associate with the spatial form of the leakage path. The spatial distribution form of the potential leakage path prediction results is generated according to the fluid conduction direction. For example, the leakage path extends from the gas path inlet to the outlet along the fluid flow direction. The path direction is consistent with the pressure gradient direction inside the equipment, and the extension length covers the range where the fluid may diffuse during the monitoring time period. During matching, if the spectral reflectance change characteristics of the target area have a high degree of overlap with the spatial direction of the leakage path, and its extension length covers at least 70% of the path prediction range, it is judged as a spatial form match.

[0056] When verifying the negative correlation between the rate of change of spectral reflectance and the fluid conduction velocity, the negative correlation is manifested as follows: when the fluid conduction velocity increases due to the increase in pressure difference, the residence time of the leaked material on the pipeline surface is shortened, resulting in a slowdown in the rate of change of spectral reflectance. For example, under high pressure difference conditions, the fluid velocity is faster, and the rate of change of spectral reflectance in the target area should be lower than that under low pressure difference conditions. If a certain area still shows a high rate of change under high pressure difference, it is determined to be an abnormal interference signal and removed. The verification process is achieved by comparing the rate of change of spectral reflectance in the same target area under different pressure conditions. For example, if the rate under high pressure difference is significantly lower than that under low pressure difference, it meets the negative correlation.

[0057] When analyzing the spatial continuity of the target area on the leakage path, spatial continuity requires that the target area is distributed along the leakage path, and the interval between adjacent areas does not exceed the preset distance. For example, the center point spacing of adjacent target areas on the leakage path must be less than twice the diameter of the pipeline. If an area is isolated and distributed outside the path or the interval exceeds the preset distance, it is considered discontinuous and eliminated. The verification of the consistency of the path conduction direction must ensure that the angle between the distribution direction of the target area and the fluid conduction direction is less than the allowable deviation. For example, when the angle between the center point connection direction of the target area and the fluid conduction direction exceeds 30 degrees, it is judged as inconsistent in direction.

[0058] When the weights of the spectral reflectivity change amplitude and spatial continuity are dynamically allocated based on the real-time pressure parameters, the weight allocation rules are dynamically adjusted according to the pressure state. For example, under high pressure, the contribution weight of the spectral reflectivity change amplitude to the leakage risk increases, while the weight of spatial continuity is relatively reduced; the opposite is true under low pressure. In specific implementation, the system automatically switches the weight allocation mode according to the range of the real-time pressure value, such as the "spectral weight priority" mode in the high-pressure interval and the "spatial continuity priority" mode in the low-pressure interval. When generating the comprehensive leakage risk assessment results, the weighted spectral reflectivity change score and spatial continuity score are combined to divide the risk level. For example, a target area has a high spectral score and a medium spatial continuity score under high pressure, and is classified as high risk after weighting; another area has a high spatial continuity score but a low spectral score under low pressure, and is classified as medium risk after weighting. The final assessment result marks the risk level and location information of the target area for targeted disposal by operation and maintenance personnel.

[0059] The optical characteristics, spatial distribution and fluid mechanics of the target area are deeply integrated. For example, the spectral reflectance of a certain area continues to decrease, and it is continuously distributed along the leakage path and in the same direction. It is given a high weight under high pressure and is determined to be a high-risk leakage point; although the spectrum of another area changes significantly, the distribution is scattered and the direction is deviated. After the weight adjustment, the risk level is reduced. The output of the assessment results includes risk level, location description and disposal suggestions, such as "the third bend of the entrance section is high risk, and it is recommended to prioritize leak detection", realizing a closed loop from data to decision-making.

[0060] Embodiment 2: Figure 2 A structural schematic diagram of an anesthesia equipment fault diagnosis system based on image recognition of the present invention is given, which includes: Image acquisition module: obtains the reference image set and dynamic image set of the transparent pipeline area of ​​the anesthesia equipment; Polarization path module: identifies microscopic deformation areas based on the changes in polarized light scattering patterns on the surface of transparent pipes in dynamic image sets, and generates potential leakage path prediction results based on the fluid conduction direction; Noise reduction and extraction module: Based on the pixel distribution characteristics of the reference image set and the potential leakage path prediction results, the ambient reflection noise in the non-leakage path area is suppressed, and the candidate area within the leakage path range with spectral differences from the noise is extracted; Disturbance verification module: Active pressure disturbance triggers the change of spectral reflectance in the candidate area, and verifies the inverse relationship between penetration rate and conduction velocity in combination with fluid conduction velocity, thus screening suspected fault areas; Threshold screening module: determines the spectral intensity fluctuation threshold of the suspected fault area, and screens the target area whose spectral intensity fluctuation exceeds the spectral intensity fluctuation threshold and overlaps with the microscopic deformation area space; Assessment generation module: Matches the spectral reflectance variation characteristics of the target area and the spatial distribution of the potential leakage path prediction results to generate leakage risk assessment results.

[0061] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product.

[0062] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application of the technical solution and the invention constraints. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0063] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0064] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0065] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An anesthesia equipment fault diagnosis method based on image recognition, characterized in that: The steps include: S1, obtaining a reference image set and a dynamic image set of a transparent pipeline area of ​​an anesthesia device; S2, based on the change of polarized light scattering pattern on the transparent pipe surface in the dynamic image set, the micro deformation area is identified, and the potential leakage path prediction result is generated in combination with the fluid conduction direction; S3, based on the pixel distribution characteristics of the reference image set and the potential leakage path prediction results, suppress the ambient reflection noise in the non-leakage path area, and extract the candidate area within the leakage path range and with a spectral difference from the noise; S4. Active pressure disturbance triggers the change of spectral reflectance in the candidate area, and verifies the inverse relationship between the permeation rate and the conduction velocity in combination with the fluid conduction velocity, thus screening the suspected fault area; S5. Determine the spectral intensity fluctuation threshold of the suspected fault area, and select the target area where the spectral intensity fluctuation exceeds the spectral intensity fluctuation threshold and overlaps with the microscopic deformation area space; S6. Match the spectral reflectance variation characteristics of the target area and the spatial distribution pattern of the potential leakage path prediction results to generate leakage risk assessment results.

2. The anesthesia equipment fault diagnosis method based on image recognition according to claim 1, characterized in that: Obtain baseline image sets and dynamic image sets of the transparent pipeline area of ​​the anesthesia equipment, including: Multispectral imaging equipment is used to collect a reference image set containing visible light bands and near-infrared bands when the transparent pipeline is leak-free. The filter band covers the characteristic absorption peak of the pipeline material under normal sealing conditions. During the operation of the anesthesia equipment, a dynamic image set containing the polarized light scattering characteristics of the pipeline surface is synchronously acquired, and the real-time pressure parameters inside the pipeline are synchronously recorded during each acquisition; The polarization filter angle is adjusted to obtain a dynamic image set with the same filter band and polarization angle as the reference image set.

3. The anesthesia equipment fault diagnosis method based on image recognition according to claim 1, characterized in that: Based on the changes in polarized light scattering patterns on the transparent pipe surface in the dynamic image set, the microscopic deformation area is identified, and the potential leakage path prediction results are generated in combination with the fluid conduction direction, including: Extract the scattered images at different polarization angles in the dynamic image set, and calculate the gray value difference of the same area on the pipeline surface at each polarization angle; Areas based on grayscale value differences exceeding the grayscale fluctuation range of the reference image set at the same polarization angle are marked as micro-deformation areas; Combining the fluid conduction direction in the gas circuit of the anesthesia equipment with the spatial distribution of the microscopic deformation area, the boundary of the microscopic deformation area is extended along the fluid conduction direction to generate a potential leakage path; The potential leakage paths whose matching degree with the normal deformation pattern of the pipeline in the reference image set is higher than the preset threshold are eliminated, and the prediction results of the potential leakage paths are retained.

4. The anesthesia equipment fault diagnosis method based on image recognition according to claim 1, characterized in that: According to the pixel distribution characteristics of the reference image set and the potential leakage path prediction results, the ambient reflection noise in the non-leakage path area is suppressed, and the candidate areas within the leakage path range and with spectral differences from the noise are extracted, including: A noise mask is generated based on the pixel grayscale distribution in the filter band of the reference image set, where the noise mask covers the environmental reflection area in the dynamic image set and the area outside the potential leakage path prediction result; Compare the spectral difference values ​​of the dynamic image set and the reference image set in the same filter band, and select the area within the leakage path where the spectral difference value exceeds the upper limit of the grayscale distribution of the noise mask as the initial candidate area; Dynamically adjust the noise suppression threshold according to the real-time pressure parameter fluctuation direction; Verify the spatial overlap ratio between the initial candidate region and the microscopic deformation region, eliminate candidate regions whose spatial overlap ratio is lower than the preset value, and retain candidate regions that meet the spatial overlap ratio and whose spectral difference values ​​meet the dynamic threshold.

5. The anesthesia equipment fault diagnosis method based on image recognition according to claim 4 is characterized in that: If the pressure fluctuation amplitude increases, the noise suppression threshold is lowered, and if the pressure fluctuation amplitude decreases, the noise suppression threshold is increased.

6. The method for anaesthesia equipment fault diagnosis based on image recognition according to claim 1, characterized in that: Active pressure disturbance triggers the change of spectral reflectance in the candidate area, and combines the fluid conduction velocity to verify the inverse relationship between the permeation rate and the conduction velocity, and screen the suspected fault area, including: Apply a pressure disturbance of a preset duration to the candidate area, and simultaneously record the change amplitude of the spectral reflectance of the candidate area in the same filter band before and after the pressure disturbance; The theoretical permeation rate threshold is calculated based on the fluid conductivity velocity, which is derived from Poiseuille's law based on the real-time pressure difference and the inner diameter of the pipeline; The candidate areas whose spectral reflectance variation amplitude is inversely proportional to the theoretical penetration rate threshold are selected as suspected fault areas; Eliminate interference areas in the candidate area where the direction of spectral reflectance change is inconsistent with the direction of pressure disturbance.

7. The method for anaesthesia equipment fault diagnosis based on image recognition according to claim 6, characterized in that: The inverse relationship verifies that the change in spectral reflectance is less than 1 / N times the theoretical permeability threshold, where N is the linear coefficient of the fluid conduction velocity.

8. The method for anaesthesia equipment fault diagnosis based on image recognition according to claim 1, characterized in that: Determine the spectral intensity fluctuation threshold of the suspected fault area, and screen the target area whose spectral intensity fluctuation exceeds the spectral intensity fluctuation threshold and overlaps with the microscopic deformation area space, including: Perform time series analysis on the spectral reflectance changes in the suspected fault area, and calculate the standard deviation of the fluctuation amplitude within the preset time window as the spectral intensity fluctuation threshold; Dynamically correct the spectral intensity fluctuation threshold based on the historical spectral fluctuation data of the normal deformation area in the reference image set, and the correction amplitude is positively correlated with the real-time pressure parameter fluctuation amplitude; The candidate regions whose spectral intensity fluctuation values ​​exceed the corrected spectral intensity fluctuation threshold and whose spatial overlap rate with the microscopic deformation region is higher than the preset overlap threshold are selected as target regions; Verify the consistency between the spectral fluctuation direction and the pressure disturbance direction of the target area, and eliminate candidate areas with reverse fluctuation directions.

9. The anesthesia equipment fault diagnosis method based on image recognition according to claim 1, characterized in that: Match the spectral reflectance variation characteristics of the target area and the spatial distribution of the potential leakage path prediction results to generate leakage risk assessment results, including: Extract the spectral reflectance change characteristics of the target area, and match the spectral reflectance change characteristics with the spatial distribution form of the potential leakage path prediction results. The matching of the spatial distribution form includes the path direction, extension length and the overlap ratio with the micro deformation area; Verify the negative correlation between the rate of change of the spectral reflectance of the target area and the fluid conduction velocity in the leakage path, and select the target area that meets the rate-velocity negative correlation; Analyze the spatial continuity of the target area on the leakage path and eliminate the isolated areas that do not meet the consistency of the path conduction direction; Based on the real-time pressure parameters, dynamic weight allocation is performed on the spectral reflectance variation amplitude and spatial continuity to generate a comprehensive leakage risk assessment result.

10. An anesthesia equipment fault diagnosis system based on image recognition, used to implement the anesthesia equipment fault diagnosis method based on image recognition according to any one of claims 1 to 9, characterized in that: include: Image acquisition module: obtains the reference image set and dynamic image set of the transparent pipeline area of ​​the anesthesia equipment; Polarization path module: identifies microscopic deformation areas based on the changes in polarized light scattering patterns on the surface of transparent pipes in dynamic image sets, and generates potential leakage path prediction results based on the fluid conduction direction; Noise reduction and extraction module: Based on the pixel distribution characteristics of the reference image set and the potential leakage path prediction results, the ambient reflection noise in the non-leakage path area is suppressed, and the candidate area within the leakage path range with spectral differences from the noise is extracted; Disturbance verification module: Active pressure disturbance triggers the change of spectral reflectance in the candidate area, and verifies the inverse relationship between penetration rate and conduction velocity in combination with fluid conduction velocity, thus screening suspected fault areas; Threshold screening module: determines the spectral intensity fluctuation threshold of the suspected fault area, and screens the target area whose spectral intensity fluctuation exceeds the spectral intensity fluctuation threshold and overlaps with the microscopic deformation area space; Assessment generation module: Matches the spectral reflectance variation characteristics of the target area and the spatial distribution of the potential leakage path prediction results to generate leakage risk assessment results.

Images