Casting quality automatic detection method for high-collapsibility sodium silicate sand casting process

Abstract

The invention relates to the technical field of quality detection, in particular to an automatic casting quality detection method for a high-collapsibility sodium silicate sand casting process. The method comprises the following steps: acquiring an ultrasonic image of a casting of a high-collapsibility sodium silicate sand casting process; screening a starting moment of the echo signal based on the echo signal and a reflection intensity difference between adjacent moments; dividing different moments into different echo signals based on the difference of the reflection intensity change rates of each moment, the adjacent moment and the starting moment; determining the possibility of the echo signal of the high-performance accelerant according to the internal reflection intensity difference and the reflection intensity of the echo signal; obtaining a high-performance promotion value of the echo signals according to the distance between the echo signals and the possibility that the echo signals are the echo signals of the high-performance accelerator in combination with the time width ratio between the echo signals; the reflection intensity is corrected based on the high-performance promotion value, and then the ultrasonic image is corrected to complete detection. According to the invention, the casting quality can be detected more accurately.

Description

Technical Field

[0001] The present application relates to the technical field of quality inspection, and in particular to an automatic inspection method for casting quality in a high-collapse water glass sand casting process. Background Art

[0002] Sodium silicate sand, a casting material made from a mixture of water glass (sodium silicate solution) and fine sand, is widely used in the foundry industry. Automated testing of casting quality during the casting process is crucial for highly collapsible water glass sand. This high collapsibility means that the sand easily breaks or crumbles during the casting process, potentially leading to surface defects or internal cracks in the casting, seriously affecting the quality and strength of the casting. Automated testing allows for real-time monitoring of casting quality, promptly identifying potential defects during the casting process, ensuring the precision and stability of the casting, and ultimately improving the quality and reliability of the casting. Ultrasonic testing, a non-destructive testing method, is commonly used to assess the quality of castings made using highly collapsible water glass sand. This method involves transmitting high-frequency sound waves into the casting and analyzing the reflected waves to assess the internal quality of the casting. When sound waves encounter media of varying densities or discontinuities, they are reflected or refracted. By measuring the time delay and intensity variation of the reflected waves, internal defects such as cracks and pores can be located and assessed.

[0003] To significantly improve the strength of water glass sand and reduce casting rejections caused by porosity and sand holes, high-performance accelerators are typically added to the sand to ensure a smooth casting process. However, uneven addition of these accelerators can lead to inconsistencies in the sand's physical properties, resulting in localized density differences. These areas of uneven density can affect the propagation of ultrasonic waves, causing them to scatter or refract during detection. This can interfere with the detection signal and prevent accurate reflection of the casting's internal quality. Summary of the Invention

[0004] In order to solve the technical problem of ultrasonic propagation interference affecting quality detection, this application provides an automatic detection method for casting quality in high-collapse water glass sand casting process. The technical solution adopted is as follows: The present application proposes a method for automatically detecting the quality of castings in a high-collapse water glass sand casting process, the method comprising the following steps: An ultrasonic probe is used to collect ultrasonic images of castings produced by a high-collapse water glass sand casting process; the horizontal axis of the ultrasonic image represents time, and the vertical axis represents reflection intensity; Determine the possibility that each moment is the starting moment based on the difference in reflection intensity between each moment and the two adjacent moments; and screen the starting moment of the echo signal based on the possibility; determine the trend similarity between each moment and the starting moment of the echo signal based on the reflection intensity change rate between each moment and its adjacent moments and the reflection intensity change rate between each moment and the starting moment of the echo signal; determine the possibility that each moment and the starting moment of the echo signal are the same echo signal based on the time difference between each moment and the starting moment of the echo signal combined with the trend similarity, and divide the moments to obtain all echo signals; determine the possibility that the echo signal is the echo signal of the high-performance accelerator based on the reflection intensity difference between each moment and its adjacent moments and the magnitude of its reflection intensity; Record any echo signal as a target signal, and determine the comparability of the echo signal to the target signal based on the likelihood that the echo signal is an echo signal of a high-performance accelerator and the distance between the echo signal and the target signal; use the proportion of each comparability as a weight, weight the time width ratio of the echo signal to the target signal, and combine the likelihood that the target signal is an echo signal of a high-performance accelerator to obtain the high-performance promotion value of the target signal; Obtaining a corrected reflection intensity at each moment according to the high performance promotion value of the echo signal and the reflection intensity at each moment, and thereby obtaining a corrected ultrasonic image; The casting quality is inspected by corrected ultrasonic images.

[0005] In the above scheme, compared with the prior art, where uneven addition of high-performance accelerators leads to local density differences, making it difficult for ultrasonic images to accurately reflect the internal quality of castings, this application solves the problem. By analyzing the waveform changes of the echo signal and comparing it with the surrounding echo signals, the influence of high-performance accelerator unevenness on the ultrasonic image is eliminated. That is, the possibility of each echo signal being a high-performance accelerator is corrected, so that the echo signal caused by high-performance accelerator unevenness becomes relatively weaker, and the echo signals of other defects become relatively stronger, so as to accurately detect the casting quality. The ultrasonic image of the high-disintegrability water glass sand casting after removing the influence of high-performance accelerator unevenness is obtained. Finally, using this optimized image, the casting quality in the high-disintegrability water glass sand casting process is accurately detected, ensuring the reliability of the casting quality.

[0006] In one embodiment, the possibility that each moment is the start moment is negatively correlated with the difference in reflection intensity between each moment and the previous adjacent moment, and positively correlated with the difference in reflection intensity between each moment and the next adjacent moment.

[0007] In one embodiment, the trend similarity is negatively correlated with the difference in the rate of change of the reflection intensity.

[0008] In one embodiment, the method of determining the possibility that each moment and the start time of the echo signal are the same echo signal based on the time difference between each moment and the start time of the echo signal in combination with trend similarity, and dividing the moments to obtain all echo signals is: The expression for the possibility of the same echo signal is: , Indicates the first The time value of the echo signal starting time, represents the time value of the hth moment in the ultrasonic image, represents an exponential function with a natural constant as the base, Indicates the hth moment and the The trend similarity of the starting time of the echo signal, Indicates the hth moment and the The possibility that the starting time of the echo signals is the same echo signal; Calculate the likelihood of each moment and the start time of all echo signals, and take each moment and the start time of the echo signal with the greatest likelihood as one echo signal; divide all moments into multiple echo signals.

[0009] In one embodiment, the possibility that the echo signal is the echo signal of the high-performance accelerator is negatively correlated with the difference in reflection intensity between each moment and the adjacent moments and the reflection intensity at each moment.

[0010] In one embodiment, the comparability of the echo signal to the target signal is negatively correlated with the likelihood that the echo signal is an echo signal of a high-performance accelerator and the distance between the echo signal and the target signal.

[0011] In one embodiment, the distance between the echo signal and the target signal is the difference in sequence numbers between the echo signal and the target signal. The sequence numbers of the echo signal and the target signal are numbered in time sequence, and the earlier the time sequence, the smaller the sequence number.

[0012] In one embodiment, the high performance enhancement value is positively correlated with the time width ratio of the echo signal and the weighted target signal, and the possibility that the target signal is an echo signal with high performance enhancement properties.

[0013] In one embodiment, the method for obtaining the corrected reflection intensity at each moment based on the high performance promotion value of the echo signal and the reflection intensity at each moment is: , Indicates the The reflection intensity at the jth moment in the echo signal, represents the high performance promotion value of the ha-th echo signal, represents an exponential function with a natural constant as the base, Indicates the The corrected reflection intensity at the jth moment in the echo signal.

[0014] In one embodiment, the method for screening the start time of the echo signal is: The probability of each moment in the ultrasonic image being the starting moment is calculated, and all moments with probabilities greater than a preset possibility threshold are regarded as the starting moments of the echo signal in the ultrasonic image.

[0015] The beneficial effects of this application are: Compared with the prior art, the present application solves the problem of uneven addition of high-performance accelerators, which leads to local density differences and makes it difficult for ultrasonic images to accurately reflect the internal quality of castings. By analyzing the waveform changes of the echo signal and comparing it with the surrounding echo signals, the influence of the unevenness of the high-performance accelerator on the ultrasonic image is eliminated. That is, the possibility of each echo signal being a high-performance accelerator is corrected, so that the echo signal caused by the unevenness of the high-performance accelerator becomes relatively weaker, and the echo signals of other defects become relatively stronger, so as to accurately detect the quality of the casting. The ultrasonic image of the high-disintegrability water glass sand casting after removing the influence of the unevenness of the high-performance accelerator is obtained. Finally, this optimized image is used to accurately detect the quality of the casting in the high-disintegrability water glass sand casting process, ensuring the reliability of the casting quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present application or the prior art, the following is a brief introduction to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0017] Figure 1 A flow chart of a method for automatically detecting casting quality for a high-collapse water glass sand casting process provided in one embodiment of the present application. DETAILED DESCRIPTION

[0018] To further illustrate the technical means and effectiveness of this application to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effectiveness of the automatic casting quality detection method for high-collapse water glass sand casting processes proposed in this application. In the following description, different references to "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

[0019] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0020] Embodiment of the automatic detection method for casting quality in a high-collapse water glass sand casting process: The specific scheme of the automatic detection method of casting quality for high-disintegrability water glass sand casting process provided by this application is described in detail below with reference to the accompanying drawings.

[0021] See also Figure 1 , which shows a flow chart of a method for automatically detecting casting quality in a high-collapse water glass sand casting process provided by one embodiment of the present application, the method comprising the following steps: Step S001: collecting ultrasonic images of castings made from a high-collapse water glass sand casting process using an ultrasonic probe.

[0022] The water glass and quartz sand are evenly mixed to form molding sand, and the molding sand is added with high-performance accelerators and disintegrators and then filled into the mold to form a casting cavity. The molten metal liquid is then added and cast into the mold to obtain the casting.

[0023] Connect the ultrasonic probe to the ultrasonic flaw detector, position the probe on the surface of the casting, and ensure that the transmitting direction of the probe is perpendicular to the surface of the casting or aligned at an appropriate angle so that the ultrasonic signal can effectively penetrate the casting and be reflected back to the probe.

[0024] The ultrasonic flaw detector then generates an ultrasonic pulse, which is transmitted through the probe into the casting. The instrument generates an ultrasonic image based on the time delay and the intensity of the echo signal. The horizontal axis of the ultrasonic image represents the echo signal's propagation time, while the vertical axis represents the echo signal's reflection intensity.

[0025] At this point, an ultrasonic image of the casting has been acquired.

[0026] Step S002: Filter the starting time of the echo signal based on the difference in reflection intensity between the echo signal and adjacent moments; and divide different moments into different echo signals based on the difference in the reflection intensity change rate between each moment and its adjacent moments; then determine the possibility of the echo signal of the high-performance accelerator based on the internal reflection intensity difference and reflection intensity of the echo signal.

[0027] In ultrasound images, the onset of an echo signal is often marked by a sharp change in reflection intensity. If the reflection intensity at a given moment varies little from the previous moment, it indicates a relatively stable signal transition, likely during the initial stages of the echo signal, where it has not yet been affected by complex reflections or diffraction. However, if the reflection intensity at that moment varies significantly from the next, it typically indicates that the echo signal is becoming more pronounced at that moment, with a sudden increase in reflection intensity. This may be due to enhanced echo signal reflection or other factors causing strong fluctuations, making this moment more likely to be the onset of the echo signal.

[0028] Therefore, the possibility of each moment being the starting moment is determined based on the difference in reflection intensity between each moment and the previous adjacent moment and the difference in reflection intensity between each moment and the next adjacent moment; this is recorded as the first possibility. The first and last moments in the ultrasound image are not considered.

[0029] The first possibility is negatively correlated with the difference in reflection intensity between each moment and the previous adjacent moment, and is positively correlated with the difference in reflection intensity between each moment and the next adjacent moment.

[0030] It should be noted that positive correlation means that when one variable increases, the other variable also increases, and the two variables change in the same direction. When one variable changes from large to small or from small to large, the other variable also changes from large to small or from small to large; the specific relationship is determined by actual application and this application does not impose any special restrictions.

[0031] It should be noted that negative correlation means that when one variable increases, the other variable decreases accordingly, and the two variables change in opposite directions. When one variable changes from large to small or from small to large, the other variable also changes from small to large or from large to small. The specific relationship is determined by actual application and this application does not impose any special restrictions.

[0032] Preferably, in this embodiment, the expression of the first possibility is: , represents the reflection intensity at the h-1th moment, represents the reflection intensity at the hth moment, represents the reflection intensity at the h+1th moment, represents the normalization function, Indicates the probability that the hth moment is the start moment.

[0033] Based on this, the probability of each moment in the ultrasound image being the start moment is calculated, and all moments with probabilities greater than a probability threshold are regarded as the start moments of the echo signals in the ultrasound image. In this embodiment, the probability threshold is 0.9. In this way, the start moments of multiple echo signals in the ultrasound image are obtained.

[0034] In the high-disintegrability water glass sand casting process, if the rate of change of the reflection intensity at any moment is close to the start of an echo signal and is equal to the rate of change at the previous moment, this indicates that the echo signal's reflection characteristics are continuous and consistent. For the same echo signal, the reflection intensity typically changes according to a certain pattern and exhibits a continuous change over time. Therefore, if the rate of change of the reflection intensity between two moments is consistent and close to the start of the echo signal, the signals at these two moments may belong to the same echo signal.

[0035] Therefore, the trend similarity between any moment and the start time of the echo signal is first determined based on the difference in the reflection intensity change rate between any moment and its adjacent moments and the reflection intensity change rate between any moment and the start time of the echo signal.

[0036] The trend similarity is negatively correlated with the difference in the reflection intensity change rate.

[0037] Preferably, in this embodiment, the expression of trend similarity is: , represents the reflection intensity at the h-1th moment, represents the reflection intensity at the hth moment, represents the time value of the h-1th moment in the ultrasonic image, represents the time value of the hth moment in the ultrasonic image, Indicates the The reflection intensity at the beginning of the echo signal, Indicates the first The time value of the starting time of the echo signal, represents an exponential function with a natural constant as the base, Indicates the hth moment and the The trend similarity of the starting time of the echo signals.

[0038] Based on the time difference between any moment and the start time of the echo signal and the trend similarity between the two, the possibility that any moment and the start time of the echo signal are the same echo signal is calculated; this is recorded as the second possibility.

[0039] Preferably, in this embodiment, the expression for the possibility of the two moments being the same echo signal is: , Indicates the first The time value of the echo signal starting time, represents the time value of the hth moment in the ultrasonic image, represents an exponential function with a natural constant as the base, Indicates the hth moment and the The trend similarity of the starting time of the echo signal, Indicates the hth moment and the The possibility that the starting time of the two echo signals is the same echo signal.

[0040] The probability of each moment and the start time of all echo signals is calculated, and the start time of each moment and the echo signal with the greatest probability is regarded as an echo signal. In this way, all moments are divided into multiple echo signals, and all echo signals in the ultrasound image are obtained.

[0041] Echo signals from defects typically show strong signal reflections on the ultrasound image, possibly accompanied by noticeable waveform changes. However, echo signals from uneven high-performance accelerators typically result in smaller signal changes, appearing as gradual waveform changes on the ultrasound image rather than distinct reflection peaks. In other words, if the reflection intensity at each moment is relatively low, and the difference from the previous moment is small, then the echo signal is likely from the high-performance accelerator.

[0042] Therefore, for each echo signal, the possibility that the echo signal is the echo signal of the high-performance accelerator is determined based on the reflection intensity differences at each moment and its adjacent moments and the magnitude of its own reflection intensity; this is recorded as the third possibility.

[0043] The third possibility is negatively correlated with the difference in reflection intensity between each moment and an adjacent moment, and the reflection intensity at each moment.

[0044] Preferably, in this embodiment, the expression of the third possibility is: , Indicates the The echo signal The reflection intensity at a moment, Indicates the The echo signal The reflection intensity at a moment, represents an exponential function with a natural constant as the base, Indicates the The number of moments in the echo signal, Indicates the The possibility that the echo signal is the echo signal of the high-performance accelerator.

[0045] The probability that all echo signals are echo signals of high-performance accelerator is calculated accordingly.

[0046] Thus, the possibility that each echo signal is an echo signal of a high-performance accelerator is obtained.

[0047] Step S003 : obtaining a high performance promotion value of the echo signal according to the distance between the echo signals and the possibility that the echo signal is the echo signal of the high performance promoter in combination with the time width ratio between the echo signals.

[0048] The primary purpose of this application is to determine whether an echo signal is that of a high-performance accelerator. Defect echo signals may have multiple internal reflection surfaces (such as crack edges or pores), and ultrasound waves will reflect multiple times between these reflection surfaces, increasing the echo signal's temporal width. High-performance accelerators, on the other hand, are homogeneous materials, making ultrasonic signal propagation simpler and resulting in a shorter temporal width. Unlike defects, which produce multiple reflections or signal broadening, ultrasound waves do not generate the same temporal widths as defects. Therefore, by comparing the temporal widths of the defect echo signal with those of the suspected high-performance accelerator, it is possible to determine whether the echo signal is that of the high-performance accelerator.

[0049] Therefore, for each echo signal, it is necessary to compare it with the time width of all echo signals. If the time width of the echo signal is shorter than the time widths of most echo signals, then the echo signal is more likely to be an echo signal belonging to a high-performance accelerator.

[0050] In order to more accurately distinguish echo signals, different weights are given to different echo signals, and the echo signal of the defect is given a higher weight. Moreover, on this basis, compared with the surrounding signals, the closer the distance, the more the defect detection sensitivity can be enhanced.

[0051] Any echo signal is recorded as the target signal. For each echo signal, its comparability to the target signal is determined based on its likelihood of being the echo signal of a high-performance accelerator and its distance from the target signal. The echo signals are sorted in chronological order and numbered according to the time sequence, with the earlier the echo signal, the smaller the number. The difference in the number is used as the distance between the echo signals.

[0052] The comparability is negatively correlated with the possibility that the echo signal is an echo signal of a high-performance accelerator and the distance between the echo signal and the target signal.

[0053] Preferably, in this embodiment, the expression of comparability is: , Indicates the possibility that the hbth echo signal on the ultrasonic image is an echo signal of high performance accelerator. Indicates the sequence number of the hath echo signal on the ultrasonic image, Indicates the sequence number of the hbth echo signal on the ultrasonic image, represents an exponential function with a natural constant as the base, represents the normalization function, Indicates the comparability of the hb-th echo signal to the ha-th echo signal.

[0054] Based on the suspected high performance accelerator properties of each echo signal on the ultrasonic image of the casting produced by the high disintegration water glass sand casting process, if the time width of each echo signal is relatively narrow compared to other comparable signals, then the probability that each echo signal is a high performance accelerator property is higher.

[0055] The time width ratio of the echo signal to the target signal is weighted with the proportion of each comparability as the weight, and the high performance promotion value of the target signal is obtained by combining the possibility that the target signal is an echo signal with high performance promoter properties.

[0056] The high performance enhancement value is positively correlated with the time width ratio between the echo signal and the weighted target signal and the possibility that the target signal is an echo signal with high performance enhancement properties.

[0057] Preferably, in this embodiment, the expression of the high performance promotion value of the target signal is: , Indicates the possibility that the hath echo signal on the ultrasonic image is an echo signal of high performance accelerator. Indicates the comparability of the hb-th echo signal to the ha-th echo signal, Indicates the number of echo signals, Indicates the time width of the hath echo signal, Indicates the time width of the hbth echo signal, represents the high performance promotion value of the hath echo signal. The target signal is the hath echo signal; and the time width is the number of all moments in the echo signal.

[0058] Based on this, a high performance boost value for each echo signal is obtained.

[0059] Thus, a high performance boost value of the echo signal is obtained.

[0060] Step S004: Correct the reflection intensity based on the high performance promotion value, and then correct the ultrasonic image.

[0061] Ultrasonic images of castings made with high-disintegrability water glass sand include echo signals from both the high-performance accelerator and defects. To ensure more accurate subsequent defect detection, this step requires determining the high-performance accelerator value for each echo signal, as described above. This weakens the echo signal caused by uneven high-performance accelerators and strengthens the echo signals of other defects. This reduces the interference of uneven high-performance accelerators on defect detection, allowing for accurate subsequent casting quality inspection.

[0062] The reflection intensity at each moment is corrected according to the high performance promotion value of the echo signal to obtain the corrected reflection intensity at each moment in the echo signal.

[0063] The expression of the corrected reflection intensity is: , Indicates the The reflection intensity at the jth moment in the echo signal, represents the high performance promotion value of the ha-th echo signal, represents an exponential function with a natural constant as the base, Indicates the The corrected reflection intensity at the jth moment in the echo signal.

[0064] Thus, the corrected reflection intensity of all echo signals at each moment is obtained, and a new ultrasonic image is drawn based on the corrected reflection intensity, thereby obtaining a corrected ultrasonic image.

[0065] At this point, the corrected ultrasonic image is obtained.

[0066] Step S005: completing the detection based on the corrected ultrasonic image.

[0067] After eliminating the effects of high-performance accelerator inhomogeneities, ultrasonic image analysis of castings made with high-disintegration sodium silicate sand focuses primarily on identifying internal defects. By analyzing echo signal characteristics such as time width, peak intensity, duration, and waveform, defects such as pores, cracks, and inclusions can be identified.

[0068] First, the time width of the echo signal can provide initial clues to the location and nature of the defect. Defects often cause echo signal broadening because ultrasonic waves, when encountering irregular reflecting surfaces or areas of varying acoustic impedance, produce multiple reflections and scattering, delaying the echo signal. Next, comparing the echo signal intensity and its changes over time can further analyze the size and location of the defect. A stronger echo signal generally indicates the presence of a defect, while abnormal fluctuations or sudden changes in signal intensity also often indicate the presence of a defect. Combining these characteristics can create a quality map of the casting's interior, pinpointing the location and type of defects.

[0069] It should be noted that the above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present application, and should all be included in the scope of protection of the present application.

[0070] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

Claims

1. An automatic detection method for casting quality in high-collapse water glass sand casting process, characterized in that: The method comprises the following steps: An ultrasonic probe is used to collect ultrasonic images of castings produced by a high-collapse water glass sand casting process; the horizontal axis of the ultrasonic image represents time, and the vertical axis represents reflection intensity; Determine the possibility that each moment is the starting moment based on the difference in reflection intensity between each moment and the two adjacent moments; and screen the starting moment of the echo signal based on the possibility; determine the trend similarity between each moment and the starting moment of the echo signal based on the reflection intensity change rate between each moment and its adjacent moments and the reflection intensity change rate between each moment and the starting moment of the echo signal; determine the possibility that each moment and the starting moment of the echo signal are the same echo signal based on the time difference between each moment and the starting moment of the echo signal combined with the trend similarity, and divide the moments to obtain all echo signals; determine the possibility that the echo signal is the echo signal of the high-performance accelerator based on the reflection intensity difference between each moment and its adjacent moments and the magnitude of its reflection intensity; Record any echo signal as a target signal, and determine the comparability of the echo signal to the target signal based on the likelihood that the echo signal is an echo signal of a high-performance accelerator and the distance between the echo signal and the target signal; use the proportion of each comparability as a weight, weight the time width ratio of the echo signal to the target signal, and combine the likelihood that the target signal is an echo signal of a high-performance accelerator to obtain the high-performance promotion value of the target signal; Obtaining a corrected reflection intensity at each moment according to the high performance promotion value of the echo signal and the reflection intensity at each moment, and thereby obtaining a corrected ultrasonic image; The casting quality is inspected by corrected ultrasonic images.

2. The automatic detection method for casting quality of high-collapse water glass sand casting process according to claim 1, wherein: The possibility that each moment is the start moment is negatively correlated with the difference in reflection intensity between each moment and the previous adjacent moment, and positively correlated with the difference in reflection intensity between each moment and the next adjacent moment.

3. The automatic detection method for casting quality of high-collapse water glass sand casting process as claimed in claim 1, wherein: The trend similarity is negatively correlated with the difference in the rate of change of reflection intensity.

4. The automatic detection method for casting quality of high-collapse water glass sand casting process as claimed in claim 1, wherein: The method of determining the possibility that each moment and the start moment of the echo signal are the same echo signal based on the time difference between each moment and the start moment of the echo signal in combination with trend similarity, and dividing the moments to obtain all echo signals is: The expression for the possibility of the same echo signal is: , Indicates the first The time value of the echo signal starting time, represents the time value of the hth moment in the ultrasonic image, represents an exponential function with a natural constant as the base, Indicates the hth moment and the The trend similarity of the starting time of the echo signal, Indicates the hth moment and the The possibility that the starting time of the echo signals is the same echo signal; Calculate the likelihood of each moment and the start time of all echo signals, and take each moment and the start time of the echo signal with the greatest likelihood as one echo signal; divide all moments into multiple echo signals.

5. The automatic detection method for casting quality of high-collapse water glass sand casting process as claimed in claim 1, wherein: The possibility that the echo signal is the echo signal of the high-performance accelerator is negatively correlated with the difference in reflection intensity between each moment and the adjacent moments and the reflection intensity at each moment.

6. The automatic detection method for casting quality of high-collapse water glass sand casting process as claimed in claim 1, wherein: The comparability of the echo signal to the target signal is negatively correlated with the possibility that the echo signal is an echo signal of a high-performance accelerator and the distance between the echo signal and the target signal.

7. The automatic detection method for casting quality of high-collapse water glass sand casting process as claimed in claim 6, wherein: The distance between the echo signal and the target signal is the difference in sequence numbers between the echo signal and the target signal. The sequence numbers of the echo signal and the target signal are numbered in time sequence, and the earlier the time sequence, the smaller the sequence number.

8. The automatic detection method for casting quality of high-collapse water glass sand casting process as claimed in claim 1, wherein: The high performance enhancement value is positively correlated with the time width ratio between the echo signal and the weighted target signal and the possibility that the target signal is an echo signal with high performance enhancement properties.

9. The automatic detection method for casting quality of high-collapse water glass sand casting process as claimed in claim 1, wherein: The method for obtaining the corrected reflection intensity at each moment based on the high performance promotion value of the echo signal and the reflection intensity at each moment is: , Indicates the The reflection intensity at the jth moment in the echo signal, represents the high performance promotion value of the ha-th echo signal, represents an exponential function with a natural constant as the base, Indicates the The corrected reflection intensity at the jth moment in the echo signal.

10. The automatic detection method for casting quality of high-collapse water glass sand casting process according to claim 1, wherein: The method for screening the start time of the echo signal is: The probability of each moment in the ultrasonic image being the starting moment is calculated, and all moments with probabilities greater than a preset possibility threshold are regarded as the starting moments of the echo signal in the ultrasonic image.

Images