Pump shell crack detection method and system for single-shell slurry pump

Abstract

The invention provides a pump shell crack detection method and system of a single-shell slurry pump, electronic equipment and a storage medium, and the method comprises the steps that a target signal of the single-shell slurry pump is obtained, and the target signal is obtained by fusing detection signals of different modes; determining a crack area of the single-shell slurry pump according to the target signal; and a crack model is constructed according to the crack area, and pump shell cracks of the single-shell slurry pump are detected through the crack model.

Description

Technical Field

[0001] The present disclosure relates to the field of electronic technology, and in particular, to a method, system, electronic device, and storage medium for detecting cracks in the pump casing of a single-casing slurry pump. Background Art

[0002] Single-casing slurry pumps are widely used in industries such as mining, metallurgy, and power to transport liquid media containing solid particles. During long-term operation, due to the corrosiveness and abrasiveness of the medium, cracks are likely to occur in the pump casing of the single-casing slurry pump. If these cracks are not detected and treated in a timely manner, it may lead to the rupture of the pump casing, resulting in serious consequences such as medium leakage and equipment shutdown. Therefore, it is of great significance to detect cracks in the pump casing of a single-casing slurry pump.

[0003] Currently, the detection of cracks in the pump casing of a single-casing slurry pump is mainly carried out by inspectors using portable detection equipment to scan the surface of the pump casing, and the presence of cracks is judged based on abnormal changes in the echo signals. For the detected cracks, manual measurement and recording are usually used for tracking and observation.

[0004] However, due to the complex curved surface structure of the pump casing of a single-casing slurry pump, the signals obtained by a single detection method are easily interfered by factors such as geometric shape and surface condition, resulting in low reliability of the detection results. Summary of the Invention

[0005] In view of this, the present disclosure provides a method, system, electronic device, and storage medium for detecting cracks in the pump casing of a single-casing slurry pump, which can improve the reliability of the detection results of cracks in the pump casing of a single-casing slurry pump.

[0006] One aspect of the present disclosure provides a method for detecting cracks in the pump casing of a single-casing slurry pump, including: Obtaining a target signal of the single-casing slurry pump, where the target signal is obtained by fusing detection signals of different modes; Determining the crack region of the single-casing slurry pump according to the target signal; Constructing a crack model according to the crack region to detect cracks in the pump casing of the single-casing slurry pump through the crack model.

[0007] According to an embodiment of the present disclosure, the obtaining of the target signal of the single-casing slurry pump includes: Obtaining an electromagnetic signal collected by an electromagnetic induction sensor disposed on a key area of the single-casing slurry pump; Obtaining an ultrasonic signal collected by an ultrasonic sensor disposed on a key area of the single-casing slurry pump; Fusing the electromagnetic signal and the ultrasonic signal to obtain a target signal.

[0008] According to an embodiment of the present disclosure, fusing the electromagnetic signal and the ultrasonic signal to obtain a target signal includes: Determine the signal-to-noise ratios of the electromagnetic signal and the ultrasonic signal respectively; Perform weighted summation on the electromagnetic signal and the ultrasonic signal according to the signal-to-noise ratios to obtain a target signal.

[0009] According to an embodiment of the present disclosure, after obtaining the target signal of the single-casing slurry pump, it further includes: Extract the high-frequency component and the low-frequency component of the target signal, where the low-frequency component characterizes the characteristics of cracks in the single-casing slurry pump; Perform denoising processing on the high-frequency component; Reconstruct the denoised high-frequency component and the low-frequency component to obtain a filtered target signal.

[0010] According to an embodiment of the present disclosure, the detection signal includes an electromagnetic signal and an ultrasonic signal. Determining the crack area of the single-casing slurry pump according to the target signal includes: Based on the extraction of the magnetic field change of the electromagnetic signal, determine the crack center; Determine the crack depth through the reflection time difference and amplitude attenuation of the ultrasonic signal; Determine the crack width according to the edge characteristics of the target signal; Determine the crack area according to the crack center, the crack depth, and the crack width.

[0011] According to an embodiment of the present disclosure, the method further includes: Obtain the flow velocity gradient, stress influence, and material wear of the single-casing slurry pump; Calculate the crack propagation correction amount based on the flow velocity gradient, stress influence, and material wear of the single-casing slurry pump; Correct the crack area based on the crack propagation correction amount.

[0012] According to an embodiment of the present disclosure, constructing a crack model according to the crack area to periodically detect the cracks in the pump casing of the single-casing slurry pump through the crack model includes: Extract the point cloud data of the crack area; Fit the point cloud data to obtain a crack model; Establish a crack prediction formula based on the crack model, and the crack prediction formula is used to characterize the evolution law of the cracks on the surface of the pump casing of the single-casing slurry pump over time.

[0013] Determine the crack length within a preset period according to the crack prediction formula.

[0014] Another aspect of the present disclosure provides a pump housing crack detection system for a single - housing slurry pump, including: A target signal acquisition module, configured to acquire a target signal of the single - housing slurry pump, where the target signal is obtained by fusing detection signals of different modalities; A crack area determination module, configured to determine the crack area of the single - housing slurry pump according to the target signal; A pump housing crack detection module, configured to construct a crack model according to the crack area, so as to periodically detect the pump housing crack of the single - housing slurry pump through the crack model.

[0015] Another aspect of the present disclosure provides an electronic device, including: One or more processors; A memory, configured to store one or more programs, wherein, when the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the method as described above.

[0016] Another aspect of the present disclosure provides a computer - readable storage medium, storing computer - executable instructions, where the instructions, when executed, are used to implement the method as described above.

[0017] According to an embodiment of the present disclosure, by fusing detection signals of different modalities to obtain a target signal, the complementary characteristics of multiple detection means can be fully utilized, effectively overcoming the signal interference problem of a single detection method on the complex curved surface structure of the pump housing. The crack area determined based on the target signal can truly reflect the distribution state of the cracks, avoiding the limitations of the scanning method of traditional portable detection devices, thereby improving the reliability of the detection result of the pump housing crack of the single - housing slurry pump. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Through the following description of the embodiments of the present disclosure with reference to the drawings, the above - mentioned and other objects, features, and advantages of the present disclosure will become clearer. In the drawings: Figure 1 Schematically shows a flowchart of a pump housing crack detection method for a single - housing slurry pump to which the present disclosure can be applied; Figure 2 Schematically shows a structural block diagram of a pump housing crack detection system for a single - housing slurry pump according to an embodiment of the present disclosure; Figure 3 Schematically shows a block diagram of an electronic device according to an embodiment of the present disclosure. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0019] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. However, it should be understood that these descriptions are merely exemplary and are not intended to limit the scope of the present disclosure. In the following detailed description, for the sake of explanation, numerous specific details are set forth to provide a thorough understanding of the embodiments of the present disclosure. However, obviously, one or more embodiments can also be implemented without these specific details. In addition, in the following description, descriptions of well-known structures and technologies are omitted to avoid unnecessarily confusing the concepts of the present disclosure.

[0020] The terms used herein are merely for describing specific embodiments and are not intended to limit the present disclosure. The terms "including", "comprising", etc. used herein indicate the presence of the described features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0021] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein should be interpreted as having a meaning consistent with the context of this specification and should not be interpreted in an idealized or overly rigid manner.

[0022] In the case of using expressions such as "at least one of A, B, and C, etc.", generally, it should be interpreted according to the meaning commonly understood by those skilled in the art (for example, "a system having at least one of A, B, and C" should include, but not be limited to, a system having only A, only B, only C, having A and B, having A and C, having B and C, and / or having A, B, and C, etc.).

[0023] The pump housing crack detection system of the single-housing slurry pump provided by the embodiments of the present disclosure can generally be arranged in a server. The pump housing crack detection method of the single-housing slurry pump provided by the embodiments of the present disclosure can also be executed by a server or a server cluster different from the server and capable of communicating with the terminal device and / or the server. Correspondingly, the pump housing crack detection system of the single-housing slurry pump provided by the embodiments of the present disclosure can also be arranged in a server or a server cluster different from the server and capable of communicating with the terminal device and / or the server. Alternatively, the pump housing crack detection method of the single-housing slurry pump provided by the embodiments of the present disclosure can also be executed by the terminal device, or can also be executed by other terminal devices different from the terminal device. Correspondingly, the pump housing crack detection system of the single-housing slurry pump provided by the embodiments of the present disclosure can also be arranged in the terminal device, or arranged in other terminal devices different from the terminal device.

[0024] It should be understood that the numbers of terminal devices, networks, and servers in the embodiments of the present disclosure are merely illustrative. According to the implementation needs, there can be any number of terminal devices, networks, and servers.

[0025] Figure 1 Schematically shown is a flowchart of a method for detecting cracks in the pump casing of a single-casing slurry pump according to an embodiment of the present disclosure.

[0026] As Figure 1 shown, the method includes steps S101 to S103.

[0027] Step S101, obtain a target signal of the single-casing slurry pump, where the target signal is obtained by fusing detection signals of different modes.

[0028] Among them, the target signal refers to a comprehensive signal obtained by fusing the electromagnetic signals collected by an electromagnetic induction sensor and the ultrasonic signals collected by an ultrasonic sensor and after signal processing. The target signal can be understood as an information carrier that can simultaneously characterize features such as the position, depth, and width of cracks on the surface of the pump casing of the single-casing slurry pump, which contains the sensitive characteristics of the electromagnetic signal to the crack position and the characterization ability of the ultrasonic signal to the crack depth. This target signal is used to accurately detect and characterize the crack distribution on a complex geometric surface, overcoming problems such as signal attenuation and detection blind spots existing in traditional single detection methods.

[0029] Based on the above embodiment, as an alternative embodiment, step S101 may further include the following steps: Step S201, obtain the electromagnetic signals collected by the electromagnetic induction sensor disposed on the key area of the single-casing slurry pump.

[0030] Step S202, obtain the ultrasonic signals collected by the ultrasonic sensor disposed on the key area of the single-casing slurry pump.

[0031] Step S203, fuse the electromagnetic signals and the ultrasonic signals to obtain the target signal.

[0032] In the embodiment of the present disclosure, the key area refers to a specific area on the surface of the pump casing of the single-casing slurry pump where stress concentration is likely to occur, wear is likely to occur, or the structure is relatively weak. Due to its special structural form and stress characteristics, the key area often becomes a high-incidence area for crack initiation and propagation, so it needs to be monitored keyly. The definition of this key area is used to guide the reasonable arrangement of sensors, ensure effective monitoring of the area where cracks are most likely to appear, and thus achieve early detection and preventive maintenance of cracks in the pump casing of the single-casing slurry pump.

[0033] Optionally, the key area may include at least one of the curved surface, inner wall corner, and reinforcing rib of the single-casing slurry pump.

[0034] Furthermore, in practical applications, there are multiple key areas on the surface of the single-casing slurry pump that need to be monitored with emphasis. For example, at the curved surface of the inlet elbow section of the pump casing, due to fluid impact and direction change, stress concentration occurs, making it prone to crack formation. In response to this situation, multiple electromagnetic induction sensors can be arranged along the inner and outer walls of the curved surface in an array distribution. The array spacing can be set to 10 - 15 mm to ensure continuous coverage of the detection area. Meanwhile, an ultrasonic sensor is set every 30 mm at the same position. Due to the divergence angle characteristic of ultrasonic waves, this spacing configuration can achieve a comprehensive scan of the curved surface.

[0035] At the inner wall corner of the pump casing, due to the sudden change in geometric shape, stress concentration often exists. For such areas, a row of electromagnetic induction sensors can be arranged on each side of the corner, and the spacing between the sensors can be set to 8 - 12 mm to improve the detection sensitivity to cracks at the corner. The ultrasonic sensor can be set at the vertex position of the corner, and the emission direction coincides with the angle bisector of the corner, so as to better capture the crack information at the corner.

[0036] For the reinforcing rib area, due to its special structural form, a more flexible sensor arrangement method is required. Electromagnetic induction sensors can be evenly arranged circumferentially at the root of the reinforcing rib with a spacing of 12 - 15 mm, so as to monitor the possible cracks at the connection between the reinforcing rib and the main structure. The ultrasonic sensor can be set at the upper part of the reinforcing rib and point to the root area at a 45-degree angle. This arrangement method can effectively detect the deep cracks at the root of the reinforcing rib.

[0037] To adapt to the curvature change of the pump casing surface, all sensors adopt a flexible installation method and are closely attached to the detection surface through a dedicated sensor fixing device. The signal wires of the sensors are designed to be waterproof and oil-proof and are effectively protected through wire grooves to ensure stable operation in the operating environment of the pump. This setting method not only ensures good coupling between the sensor and the detection surface but also facilitates daily maintenance and replacement.

[0038] It should be noted that the way of setting the electromagnetic induction sensor and the ultrasonic sensor in the key area is only exemplary. In practical applications, it can be flexibly adjusted according to the specific model, working conditions, structural characteristics, and monitoring requirements of the single-casing slurry pump. For example, for a slurry pump operating under high-abrasion conditions, the arrangement density of the sensors can be appropriately increased; for pump casings of different diameters, the spacing and coverage range of the sensors can be adjusted accordingly; for pump bodies in special working environments, different protection-grade sensor installation methods can also be selected according to environmental factors. In addition, the specific installation angle, position, and quantity of the sensors can also be optimized and adjusted based on actual operating experience and professional evaluation results to achieve the best monitoring effect. The specific setting method of the sensors in the embodiments of the present disclosure is not uniquely limited.

[0039] In the above embodiments, by arranging electromagnetic induction sensors and ultrasonic sensors in the key areas of the single-casing slurry pump and fusing the collected electromagnetic signals and ultrasonic signals, the following technical effects can be achieved: Due to the particularity of the key areas, complex geometric structures such as curved surfaces, inner wall corners, and stiffeners are prone to stress concentration and wear. By adopting the dual monitoring method of electromagnetic induction sensors and ultrasonic sensors, the limitations of a single detection method can be effectively overcome. The electromagnetic induction sensor has a high detection sensitivity to the position of cracks and can timely detect the generation of surface micro-cracks; while the ultrasonic sensor has good depth detection ability and can accurately characterize the depth information of cracks. By fusing and processing the signals collected by the two sensors, both the precise positioning ability of the electromagnetic signal for the crack position and the characterization advantage of the ultrasonic signal for the crack depth are retained, thus improving the accuracy of crack detection.

[0040] Based on the above embodiments, as an alternative embodiment, step S203 may specifically further include the following steps: Step S301, respectively determine the signal-to-noise ratios of the electromagnetic signal and the ultrasonic signal.

[0041] Step S302, perform weighted summation on the electromagnetic signal and the ultrasonic signal according to the signal-to-noise ratios to obtain the target signal.

[0042] Among them, the signal-to-noise ratio of the signal is an important indicator to measure the signal quality. In the crack detection of the pump casing of the single-casing slurry pump, due to the complex working environment and detection conditions, the electromagnetic signal and the ultrasonic signal are often disturbed to varying degrees. These interferences may come from the vibration of the pump body, the fluctuation of the environmental electromagnetic field, the inhomogeneity of the medium, and various noises generated by the operation of the equipment. Therefore, before signal fusion, it is necessary to respectively determine the signal-to-noise ratios of the electromagnetic signal and the ultrasonic signal to evaluate the reliability of each signal.

[0043] Furthermore, by calculating the signal-to-noise ratio, not only can the quality status of each signal be evaluated, but also the abnormal fluctuations in the signal can be identified. For example, when a certain sensor is strongly interfered or fails, the signal-to-noise ratio of its output signal will be significantly reduced, and the system can accordingly reduce the weight of this signal in the fusion process or even temporarily block the input of this signal to ensure the reliability of the fusion result.

[0044] After obtaining the signal-to-noise ratios of the electromagnetic signal and the ultrasonic signal, it is necessary to effectively combine the two signals through weighted fusion to make full use of their respective advantageous features. The electromagnetic signal is more sensitive to the change of the crack position, while the ultrasonic signal has an advantage in crack depth measurement. Through reasonable weight allocation and signal fusion, more comprehensive and accurate crack feature information can be obtained.

[0045] Exemplarily, it is defined that an electromagnetic induction sensor collects the changes in electromagnetic characteristics near the crack of the pump casing, and the generated electromagnetic signal is ; the ultrasonic sensor emits ultrasonic signals and records the reflected signals, and the generated ultrasonic signal is .

[0046] Normalize the electromagnetic signal and the ultrasonic signal respectively: ; Dynamically adjust the weights of the signals according to the signal-to-noise ratio (SNR) and : ; Perform weighted summation to generate the target signal: .

[0047] Based on the above embodiments, as an alternative embodiment, after step S101, the following steps may further be included: Step S401, extract the high-frequency component and the low-frequency component of the target signal, and the low-frequency component characterizes the characteristics of the crack in the single-casing slurry pump.

[0048] Step S402, perform denoising processing on the high-frequency component.

[0049] Step S403, reconstruct the denoised high-frequency component and the low-frequency component to obtain the filtered target signal.

[0050] During the detection of the crack in the pump casing of the single-casing slurry pump, the target signal contains various frequency components. Among them, the low-frequency component mainly reflects the basic characteristics of the crack, while the high-frequency component contains noise information such as vibrations generated by equipment operation and environmental interference. In order to accurately extract the crack characteristics, it is necessary to perform frequency decomposition on the target signal to separate signal components with different physical meanings.

[0051] Performing multi-scale decomposition on the target signal through wavelet transform can achieve local analysis of the signal in the time-frequency domain. Wavelet transform has good time-frequency localization characteristics and can capture the detailed changes of the signal at different scales. During the decomposition process, it is particularly important to select an appropriate wavelet basis function, and the similarity between the wavelet function and the crack characteristic signal needs to be considered to improve the accuracy of feature extraction. For example, for the step-type signal change caused by the crack, a wavelet basis function with good edge-preserving performance can be selected.

[0052] In practical applications, the existence of cracks will lead to changes in the local structural characteristics of the pump casing. This change is manifested as a relatively slow change trend in the signal, mainly in the low-frequency components. Through wavelet decomposition, this slow-varying feature can be effectively separated from high-frequency noise. The low-frequency components not only contain the position information of the cracks but also reflect geometric features such as the depth and width of the cracks. These characteristic information is of great significance for evaluating the severity of the cracks. At the same time, wavelet decomposition can also preserve the time-domain characteristics of the signal, which helps to determine the precise position of the cracks.

[0053] After obtaining the high-frequency components of the signal, effective denoising processing is required to improve the signal quality. This is because the high-frequency components mainly contain interference information such as vibration noise during equipment operation, environmental electromagnetic interference, and random noise of the measurement system itself. These noises will affect the accurate extraction of crack characteristics. At the same time, the high-frequency components may also contain some useful crack edge information. Therefore, the denoising process needs to strike a balance between suppressing noise and retaining useful information.

[0054] Noise and signals have different distribution characteristics in the wavelet domain. The useful components of the signal are manifested as relatively large amplitudes in the wavelet coefficients, while the noise shows a random distribution with relatively small amplitudes. Based on this characteristic, the threshold denoising method can effectively distinguish and process these two types of components. In specific implementation, first, an appropriate threshold needs to be determined, and then the coefficients smaller than the threshold are processed to achieve noise suppression. An overly large threshold will cause the useful signal to be overly suppressed, resulting in signal distortion; an overly small threshold cannot effectively remove the noise. To solve this problem, an adaptive threshold determination method can be adopted to dynamically adjust the threshold size according to the statistical characteristics of the signal.

[0055] After completing the denoising processing of the high-frequency components and retaining the low-frequency components, these two parts of the signal need to be effectively reconstructed to obtain the complete target signal. The purpose of signal reconstruction is to reasonably combine the low-frequency components containing the main characteristics of the cracks with the denoised high-frequency components to form a complete signal that not only retains the crack characteristics but also has a high signal-to-noise ratio.

[0056] Signal reconstruction uses an inverse transformation process corresponding to wavelet decomposition to synthesize signal components in different frequency bands. During the reconstruction process, the low-frequency components contain the basic characteristic information of the cracks, such as key parameters like the position and depth of the cracks; while the denoised high-frequency components retain the detailed characteristics of the crack edges. These detailed information is of great significance for accurately judging the shape and development trend of the cracks. Through a reasonable reconstruction algorithm, it can be ensured that these two types of information are effectively fused during the reconstruction process.

[0057] In practical applications, the selection of the reconstruction algorithm needs to consider the balance between computational efficiency and reconstruction accuracy. The use of the fast wavelet reconstruction algorithm can improve the processing speed and meet the requirements of real-time detection. At the same time, by optimizing the reconstruction parameters, such as the selection of wavelet basis functions and the determination of the reconstruction level, it can be ensured that the reconstructed signal retains the effective information of the original signal to the greatest extent.

[0058] Exemplarily, for the target signal ; perform wavelet transform to obtain the low-frequency component .

[0059] In the wavelet domain, set a threshold T for the high-frequency component for denoising: ; Reconstruct the denoised high-frequency component and the low-frequency component to obtain the filtered target signal: .

[0060] Step S102, determine the crack area of the single-case slurry pump according to the target signal.

[0061] After obtaining the target signal of the single-case slurry pump, it is necessary to determine the crack area of the single-case slurry pump according to this target signal. Since the surface of the pump casing of the single-case slurry pump has complex geometric features, such as curved surfaces, inner wall corners, and stiffeners, etc., these special areas are often the positions where stress concentration occurs and cracks are likely to occur.

[0062] In the embodiments of the present disclosure, the crack area refers to the local spatial range where structural damage appears on the surface of the pump casing of the single-case slurry pump. This area usually shows the interruption or separation of material continuity. The crack area can be understood as a three-dimensional space range jointly defined by three key parameters: the crack center coordinates, the crack depth, and the crack width. Among them, the crack center coordinates determine the position distribution of the crack on the pump casing surface, the crack depth characterizes the extension degree of the crack in the direction perpendicular to the surface, and the crack width describes the spread range of the crack in the horizontal direction.

[0063] Based on the above embodiments, as an optional embodiment, step S102 may further include the following steps: Step S301, determine the crack center based on the extraction of the magnetic field change of the electromagnetic signal.

[0064] Specifically, during the crack detection process of the pump casing of the single-case slurry pump, the existence of the crack will cause the material continuity to be damaged, thereby causing significant changes in the local magnetic permeability and magnetic resistance. This change will leave a characteristic "magnetic field fingerprint" in the electromagnetic signal collected by the electromagnetic induction sensor. By analyzing this magnetic field change characteristic, the center position of the crack can be accurately located.

[0065] The embodiments of the present disclosure adopt a method based on gradient analysis to extract the magnetic field change characteristics of electromagnetic signals. First, the original signals collected by the electromagnetic induction sensors are preprocessed, including signal denoising and baseline correction, to eliminate the interference caused by environmental magnetic field fluctuations and equipment operation. Then, the rates of change of the processed signals in the horizontal and vertical directions are calculated to construct a complete gradient field distribution. The gradient field not only reflects the spatial change trend of the magnetic field strength but also highlights the mutation characteristics at the edges of the fissures. At the fissure positions, due to the fracture of the material, the magnetic field changes violently, forming significant peak regions in the gradient field.

[0066] To accurately extract the fissure center position from the gradient field, this embodiment designs an adaptive threshold screening method. This method first determines the initial threshold based on the statistical characteristics of the signals, and marks the regions where the gradient modulus value is greater than the threshold as candidate fissure regions. In the candidate regions, a local extreme value detection algorithm is used to find the peak points of the gradient field, and these peak points usually correspond to the center positions of the fissures.

[0067] In practical applications, considering that the geometric characteristics of the pump shell surface may affect the magnetic field distribution, this embodiment also adopts a differential processing strategy for different key regions. For example, in the curved surface region, the influence of curvature on the magnetic field distribution needs to be considered, and the gradient calculation is corrected by introducing a curved surface coordinate transformation. At the inner wall corners, due to the sudden change in geometric shape, the magnetic field may be distorted, and the system will comprehensively analyze the data from multiple sensors to improve the positioning accuracy. For the ribbed region, special attention needs to be paid to the magnetic field change characteristics caused by stress concentration.

[0068] Exemplarily, for the determination of the fissure center, first, the electromagnetic signals are subjected to gradient calculation to obtain the gradient field : ; In the formula, and are the rates of change of the signal in the x and y directions respectively, and i and j are the unit vectors in the x and y directions.

[0069] Among them, the modulus value of the gradient represents the intensity of the signal change, and the fissure center region usually corresponds to the local maximum value of the gradient modulus value.

[0070] The threshold method is used to extract the regions with larger gradients, and all the points that meet the following conditions are marked as candidate fissure positions: ; In the formula, is the empirically set gradient threshold.

[0071] In the candidate fissure regions, the extreme value points of the local gradient modulus are calculated to determine the fissure center , thus obtaining the center of the crack.

[0072] Step S302: Determine the crack depth based on the reflection time difference and amplitude attenuation of the ultrasonic signal.

[0073] Specifically, when ultrasonic waves encounter a material interface or defect during propagation, reflections will occur. This reflected signal carries rich depth information. By analyzing the reflection time difference and amplitude attenuation characteristics of the ultrasonic signal, the extent of the crack's extension in the depth direction can be accurately measured.

[0074] In actual detection, the ultrasonic sensor emits ultrasonic pulses towards the pump shell material and receives the echo signal reflected from the crack surface. Since the propagation speed of ultrasonic waves in the material is basically constant, the crack depth can be calculated by measuring the time difference between the emission and reception of the ultrasonic waves. The system first performs time-domain analysis on the received ultrasonic signal to determine the arrival time of the reflected wave by identifying the peak or mutation point of the signal. At the same time, the ultrasonic signal will undergo amplitude attenuation during propagation, and this attenuation degree is closely related to the propagation distance. By establishing the corresponding relationship between amplitude attenuation and propagation distance, additional verification basis can be provided for depth measurement.

[0075] Exemplarily, for the calculation of the crack depth, time-domain analysis of the ultrasonic signal is required to extract the time points of the reflected signal , and use time-domain features (such as signal peaks or mutation points of arrival time) to identify the crack reflection signal. According to the round-trip time of ultrasonic wave propagation combined with the wave speed , calculate the depth of the crack : .

[0076] Step S303: Determine the crack width based on the edge features of the target signal.

[0077] Specifically, the crack width reflects the degree of fracture of the material in the transverse direction and is an important parameter for evaluating the development state of the crack and predicting the expansion trend. In this embodiment, the crack width is determined by analyzing the edge features of the target signal because the target signal, as the fusion result of electromagnetic signals and ultrasonic signals, can more comprehensively reflect the transverse distribution characteristics of the crack.

[0078] Furthermore, edge enhancement preprocessing of the target signal is first required. The system adopts an adaptive edge enhancement algorithm to highlight the edge contour information in the target signal through local contrast adjustment and gradient sharpening. The enhanced signal is processed by an edge detection operator to obtain a clear edge feature map. In the edge feature map, the crack area usually shows a pair of obvious parallel edge lines, and the position and intensity of these edge lines directly reflect the transverse range of the crack.

[0079] To accurately extract the crack boundary, the system establishes a local coordinate system near the determined crack center position and searches for edge features along the direction perpendicular to the crack trend. By analyzing the distribution curve of the edge intensity, the system can identify two position points where the edge intensity reaches a significant peak, and these two position points are the left and right boundaries of the crack. To improve the reliability of boundary extraction, the system also adopts sub-pixel edge localization technology. By interpolating and fitting the edge intensity curve, a more precise boundary position can be determined.

[0080] Exemplarily, for the calculation of the crack width, an edge detection algorithm needs to be applied to the target signal to obtain edge features , near the crack center , find two boundary points with significant edge feature intensity and . Calculate the crack width : .

[0081] Step S304, determine the crack area according to the crack center, crack depth, and crack width.

[0082] Specifically, after obtaining these three key parameters of the crack center, depth, and width, these discrete feature parameters need to be integrated into a complete description of the crack area. The determination of the crack area not only needs to consider the numerical values of each parameter but also needs to reflect the spatial distribution characteristics and morphological features of the crack.

[0083] When constructing the crack area, first, take the crack center coordinates as the reference point to establish a local coordinate system. In this coordinate system, the crack depth defines the vertical extension range, and the crack width determines the horizontal spread range. Through these parameters, the system can construct a preliminary spatial distribution model. For cracks with relatively regular shapes, their spatial ranges can be directly described by mathematical expressions; while for cracks with irregular shapes, more complex modeling methods are required.

[0084] To improve the accuracy of area description, the system adopts point cloud reconstruction technology. By collecting dense feature points on the crack surface and combining the depth information obtained above, three-dimensional point cloud data representing the crack morphology can be generated. After these point cloud data are processed by surface fitting, they can more realistically reflect the spatial distribution characteristics of the crack. At the same time, the system also considers the transition characteristics of the crack edge. By introducing a weight function to describe the fuzzy characteristics of the boundary area, the area description can be made more in line with the actual situation.

[0085] Exemplarily, for the determination of the crack area, first, a spatial distribution model of the crack needs to be established. The spatial range of the crack area can be described by the following formula:

[0086] Assume that the fracture area is a regular cuboid, and the above formula range description can be directly used; if the fracture shape is irregular, the point cloud reconstruction algorithm is combined to further fit the spatial distribution of the fracture.

[0087] However, in a single-shell slurry pump, the movement of the fluid inside the pump casing is not symmetric. Especially near the volute, the impeller inlet and outlet, the flow velocity distribution is highly uneven. This asymmetric flow causes different scouring effects of the fluid on the pump casing material, making the fracture expand faster along the high-flow velocity direction; in the high-flow velocity area, the width expansion rate of the fracture is greater, resulting in an asymmetric shape of the fracture area.

[0088] In a single-shell slurry pump, the fracture propagation is affected by the following factors: Fluid scouring effect: The fracture propagates faster in high-flow velocity areas (such as the volute and the impeller inlet); (2) Stress distribution: There is a large fluid pressure gradient near the impeller outlet, resulting in stress concentration; (3) Material wear: The fracture propagation rate is larger in high-wear areas, and the material structure is weakened.

[0089] Therefore, it is necessary to calculate the flow velocity gradient field V(x, y) based on computational fluid dynamics (CFD) simulation and perform adaptive correction on the fracture area.

[0090] Based on the above embodiments, as an alternative embodiment, the following steps may further be included: Step S601, obtain the flow velocity gradient, stress influence, and material wear of the single-shell slurry pump.

[0091] Among them, in the embodiments of the present disclosure, the flow velocity gradient of the single-shell slurry pump refers to the rate of change of the fluid velocity inside the pump casing in space, and this rate of change characterizes the difference degree of the fluid velocity vector at different positions. In the embodiments of the present disclosure, it can be understood as a physical quantity describing the non-uniformity of the internal flow field of the single-shell slurry pump. Its magnitude reflects the speed of change of the fluid velocity between adjacent positions, and the direction indicates the spatial direction in which the velocity changes most significantly. The flow velocity gradient of the single-shell slurry pump is used to characterize the scouring action intensity of the fluid on the pump casing material, evaluate the asymmetric propagation trend of the fracture in different areas, and provide an important basis for predicting the fracture propagation direction.

[0092] Exemplarily, in order to accurately obtain the flow velocity gradient distribution inside the single-shell slurry pump, this embodiment uses the computational fluid dynamics (CFD) simulation method to establish an internal flow field model of the slurry pump. Since the internal flow of the slurry pump has highly nonlinear and asymmetric characteristics, especially there are complex three-dimensional flow phenomena in areas such as the volute and the impeller outlet, it is necessary to obtain detailed flow field information through numerical simulation methods.

[0093] When establishing the CFD model, first construct a three-dimensional computational domain according to the actual geometric dimensions of the pump casing and impeller, and perform spatial discretization using a hybrid structured and unstructured grid. Considering the non-Newtonian fluid characteristics of the slurry, select the k-ε turbulence model to describe the flow characteristics, and adopt an enhanced wall treatment method in the near-wall region to improve the calculation accuracy. By solving the continuity equation and momentum equation, the velocity distribution of the flow field can be obtained, and then the velocity gradient can be calculated: Calculate the velocity gradient: ; The simulation results show that in the volute region, due to the sudden change in the cross-sectional area of the flow channel and the change in the fluid direction, the maximum velocity gradient ∇V is generated, which leads to a significant increase in the crack propagation rate in this region. Based on this feature, this embodiment sets a correction amount considering the influence of the velocity gradient: ; Among them, the correction coefficient can be obtained by fitting using the least squares method with a large amount of experimental data. This method of setting the correction amount based on the velocity gradient can effectively reflect the influence of the hydrodynamic action on crack propagation, especially the asymmetric propagation characteristics in the high velocity gradient region.

[0094] Among them, the stress influence of the single-casing slurry pump refers to the internal stress state of the material caused by factors such as mechanical loads, fluid pressure, and temperature changes borne by the pump casing during operation. In the embodiment of the present disclosure, it can be understood as a physical quantity that comprehensively reflects the stress condition of the local area of the pump casing. This physical quantity not only includes the stress distribution under the action of fluid pressure, but also considers the thermal stress caused by fluid temperature and the influence of the strength of the pump casing material.

[0095] Exemplarily, in order to accurately calculate the stress distribution inside the pump casing of the single-casing slurry pump, this embodiment uses the finite element analysis method to establish a mechanical model considering the fluid-structure coupling effect. Since the pump casing is simultaneously subjected to the combined action of fluid pressure, temperature change, and structural load during operation, the coupling effect of these factors will lead to a complex stress distribution, especially in the region of structural mutation, stress concentration is likely to form. Therefore, detailed stress field information needs to be obtained through precise numerical calculation methods.

[0096] When establishing the finite element model, first construct a three-dimensional solid model according to the actual structural characteristics of the pump casing, and perform spatial discretization using the adaptive grid technology, and locally refine the grid in the expected stress concentration region. Considering the elastoplastic characteristics and temperature dependence of the material, select a suitable constitutive model to describe the material behavior. By solving the equilibrium equation considering multi-field coupling, the stress distribution of the pump casing can be obtained: ; In the formula, represents the fluid pressure; represents the fluid temperature; Represents the material strength of a single - shell slurry pump; Set the stress correction amount: ; Wherein, It is determined by material experiments. The experimental process simulates the stress state of the pump casing under actual working conditions, and obtains material parameters through the measurement of the stress - strain relationship.

[0097] Among them, the material wear of the single - shell slurry pump refers to the phenomenon of surface material loss of the pump casing during long - term operation due to the impact, shear, and friction of solid particles in the slurry. In the embodiments of the present disclosure, it can be understood as a physical quantity characterizing the degree of thinning of the material thickness in a local area of the pump casing, and this physical quantity is quantitatively described by the wear layer thickness M(x, y) to represent the material loss condition at different positions.

[0098] Exemplarily, in order to accurately evaluate the material wear condition of the surface of the single - shell slurry pump casing, in this embodiment, an eddy current sensor is used for non - destructive testing of the pump casing surface. When performing wear measurement, first, a special eddy current sensor detection system is designed according to the geometric characteristics of the pump casing, the array layout is adopted to improve the detection efficiency, and continuous monitoring of the pump casing surface is realized through an automatic scanning device. Considering the accessibility and detection accuracy requirements of different regions, the excitation frequency and detection sensitivity of the sensor are optimized. By analyzing the amplitude and phase changes of the eddy current signal, the surface wear layer thickness M(x, y) can be obtained.

[0099] Based on the measured wear data, a correction amount considering the influence of material wear is set: ; where Is obtained by fitting experimental data.

[0100] Step S602, calculate the crack propagation correction amount based on the flow velocity gradient, stress influence, and material wear of the single - shell slurry pump.

[0101] Specifically, in this embodiment, by weighted superposition of the flow velocity gradient correction amount, stress correction amount, and wear correction amount, a complete crack propagation correction amount is constructed: ; That is, .

[0102] In practical applications, the correction amounts exhibit obvious differential characteristics in different regions of the pump casing. In the volute region, due to the simultaneous presence of a high flow velocity gradient and significant stress concentration, and severe material wear caused by long-term operation, all three correction terms reach relatively large values, resulting in the maximum value of f(V), which accurately reflects the rapid crack propagation characteristics in this region. In the impeller outlet region, although there is a high stress concentration, due to the relatively low flow velocity gradient and general wear degree, the overall correction amount is less than that in the volute region, indicating that the crack propagation rate at this location is relatively slow. In the low-flow-velocity region of the pump casing far from the impeller, since the flow velocity gradient, stress level, and wear degree are all low, the three correction terms approach zero, making f(V) approach zero.

[0103] Step S603: Correct the crack region based on the crack propagation correction amount.

[0104] Specifically, since the crack region of the single-casing slurry pump exhibits obvious asymmetric propagation characteristics under actual working conditions, it is difficult to accurately describe its evolution law relying only on the initial crack geometric parameters. Especially in regions with a large flow velocity gradient, significant stress concentration, and severe material wear, the actual crack propagation rate and direction will deviate significantly. Therefore, it is necessary to use the calculated crack propagation correction amount f(V) to dynamically correct the crack region to obtain a more realistic crack propagation prediction result.

[0105] Furthermore, the correction formula for the crack region by the crack propagation correction amount f(V) can be defined as follows: In the formula, is the correction amount of the flow velocity gradient field V(x, y) to crack propagation.

[0106] The above dynamic adjustment method for the crack region based on the correction amount can accurately reflect the asymmetric crack propagation behavior in the single-casing slurry pump. For example, in the volute region, due to the relatively large correction amount f(V), the depth and width of the crack increase faster, and the propagation direction will deviate towards the high-flow-velocity side; while in the low-flow-velocity region, the correction amount is small, and the crack basically maintains symmetric propagation. Through the correction method of the multi-factor coupling effect, the accuracy of crack propagation prediction can be improved according to the differential characteristics of the single-casing slurry pump.

[0107] Step S103: Construct a crack model based on the crack region to detect the cracks in the pump casing of the single-casing slurry pump through the crack model.

[0108] Among them, the crack model refers to a theoretical model constructed by mathematical methods to characterize the spatial distribution and evolution characteristics of cracks on the surface of the single-shell slurry pump casing. In the embodiments of the present disclosure, it can be understood as an organic combination of a three-dimensional geometric model reconstructed based on point cloud data and a crack propagation prediction model established based on physical properties. This model not only includes the static geometric characteristics of cracks but also incorporates dynamic change information in the time dimension. The crack model is used to achieve visual presentation of the pump casing cracks, prediction of the expansion trend, and risk assessment, providing a theoretical basis for preventive maintenance and service life assessment of the pump casing.

[0109] Based on the above embodiments, as an alternative embodiment, step S103 may further include the following steps: Step S701, extract the point cloud data of the fissure area.

[0110] Specifically, after determining the fissure area, it is necessary to extract the point cloud data of this area to accurately describe the fissure morphology. Since the fissure area usually exhibits irregular three-dimensional spatial distribution characteristics, it is difficult to completely express the geometric morphology of the fissure only relying on discrete parameters such as the fissure center, depth, and width. By generating densely distributed spatial sampling points, the shape characteristics of the fissure can be more carefully depicted, providing a complete data basis for subsequent model reconstruction.

[0111] Specifically, first, a local coordinate system is established with the fissure center coordinates as the reference point. In this coordinate system, the sampling space range is determined based on the obtained fissure depth and fissure width. Considering the morphological feature differences of the fissure in different regions, an adaptive sampling strategy needs to be adopted. In the regions where the fissure edge and depth change significantly, the point cloud density is increased by reducing the sampling interval; while in the regions with gentle morphological changes, the sampling interval can be appropriately increased to improve the data processing efficiency. Exemplarily, the sampling interval in the fissure edge region can be set to 0.1 mm, while in the central region, it can be relaxed to 0.5 mm.

[0112] Furthermore, to ensure that the sampling points can accurately reflect the geometric characteristics of the fissure surface, this embodiment adopts a sampling density control method based on curvature. By calculating the local surface curvature, the number of sampling points is automatically increased in the regions with larger curvature. At the same time, considering the material properties and surface state of the single-shell slurry pump casing, the influence of material anisotropy and surface roughness also needs to be considered during the sampling process. The sampling position is fine-tuned by introducing a compensation factor to improve the accuracy of the point cloud data.

[0113] Each sampled point collected contains spatial coordinate information and surface feature parameters. The spatial coordinates are used to determine the exact position of the point, while the surface feature parameters include information such as the normal vector and curvature at that point. These additional information helps to improve the accuracy of subsequent surface reconstruction. To ensure the reliability of the data, the system also performs outlier detection and filtering on the collected point cloud data to remove the noise points caused by measurement errors or environmental interference.

[0114] Step S702, fit the point cloud data to obtain a fracture model.

[0115] Since the original point cloud data is a set of discrete spatial coordinate points, it is difficult to directly use it for the analysis and prediction of fracture characteristics. It is necessary to convert these discrete points into a continuous surface model through appropriate mathematical methods to accurately represent the geometric shape and topological structure of the fracture.

[0116] Exemplarily, the embodiments of the present disclosure can use the Delaunay triangulation algorithm to reconstruct the point cloud data. The core idea of this algorithm is to approximate the fracture surface by constructing an optimal triangular mesh while maintaining the data topological relationship. First, preprocess the point cloud data, including spatial coordinate transformation and outlier removal. In the local coordinate system, use the principal component analysis method to determine the main direction of the point cloud and project the point cloud onto the best-fitting plane. This preprocessing can reduce the complexity of subsequent surface reconstruction and improve the fitting accuracy.

[0117] After completing the preprocessing, the system constructs an initial triangular mesh based on the point cloud data. To improve the mesh quality, an iterative optimization strategy is used to refine and smooth the mesh. During the mesh refinement process, dynamically adjust the size and shape of the triangles according to the local curvature information to ensure a high mesh density in the regions with significant features such as the fracture edge. At the same time, eliminate the noise and irregularities on the mesh surface through algorithms such as Laplacian smoothing to make the reconstructed surface smoother and more continuous.

[0118] To accurately describe the depth change of the fracture, this embodiment also introduces a B-spline based surface fitting method. By constructing a control point grid on the basis of the triangular mesh and using B-spline basis functions for surface interpolation, a fracture surface model with good continuity can be obtained. This method can not only maintain the overall morphological characteristics of the fracture but also accurately depict local details by adjusting the weights of the control points.

[0119] During the surface reconstruction process, the physical constraint conditions of the fracture also need to be considered. For example, the change of the normal vector on the fracture surface should be continuous, and the fracture depth should satisfy the basic laws of material mechanics. By introducing these constraint conditions into the fitting algorithm, it can be ensured that the reconstructed fracture model is not only geometrically accurate but also can reflect the actual physical characteristics of the fracture.

[0120] Step S703: Establish a crack prediction formula based on the crack model. The crack prediction formula is used to characterize the evolution law of cracks on the surface of the single - shell slurry pump casing over time.

[0121] Among them, the crack prediction formula refers to the described mathematical expression, which comprehensively considers multiple influencing factors such as the initial crack length, material property coefficient, stress state, etc. In the embodiments of the present disclosure, it can be understood as a mathematical model based on fracture mechanics theory that includes the time dimension, and this model expresses the crack length as a functional relationship of time and other physical parameters. The crack prediction formula is used to calculate the crack length and propagation rate at a specific time point, providing a quantitative basis for evaluating the damage degree of the pump casing and predicting the remaining service life.

[0122] After obtaining the crack model, it is necessary to establish a crack prediction formula to achieve quantitative prediction of the crack development trend. Since during the operation of the single - shell slurry pump, the cracks on the pump casing will continue to expand under the influence of various factors such as cyclic stress and material fatigue, relying solely on the static geometric model cannot reflect the dynamic evolution characteristics of the cracks. Therefore, it is necessary to establish a prediction formula that includes the time dimension to evaluate the extent of crack expansion at future time points.

[0123] The embodiments of the present disclosure construct a crack prediction formula based on the material fracture mechanics theory. This formula takes the initial crack length, material property coefficient, stress state, and operation time as key variables, and describes the crack propagation process by establishing the mathematical relationship between them. Among them, the initial crack length is obtained through geometric analysis of the current crack model; the material property coefficient reflects the fatigue characteristics and crack propagation performance of the material, and needs to be determined through special material tests; the stress state is calculated according to the actual working conditions of the pump casing.

[0124] To ensure the accuracy of the prediction formula, it is necessary to consider the anisotropy of the pump casing material and the influence of environmental factors. By introducing the material directionality coefficient and environmental correction factor, the crack propagation behavior under actual working conditions can be more accurately described. At the same time, considering the relationship between the crack propagation rate and the stress intensity factor, the influence of the stress intensity factor also needs to be included in the prediction formula.

[0125] The establishment of the prediction formula can adopt the progressive analysis method. First, a basic equation is constructed based on the theoretical model, and then it is verified and corrected through experimental data. On the basis of considering various influencing factors, an expression that can describe the change of crack length over time is obtained through mathematical derivation.

[0126] Exemplarily, the construction of the crack prediction formula is as follows: ; In the formula, is the initial crack length obtained through detection, is the material coefficient, related to the fatigue characteristics and crack propagation performance of the material, and can be determined through experiments; is the stress at the crack; is the operating time.

[0127] Step S704, determine the crack length within a preset period according to the crack prediction formula.

[0128] Since the continuous expansion of cracks will directly affect the operating safety of the equipment, by calculating the crack length within a preset period, potential risks can be detected in a timely manner, providing a specific time reference for equipment maintenance.

[0129] Obtain the initial crack length through the analysis of the current crack model, determine the material coefficient in combination with experimental data, and calculate the stress state based on the actual operating conditions of the pump casing. After obtaining these basic parameters, substitute them into the crack prediction formula, and obtain the crack length values at different time points within the preset period through numerical calculation.

[0130] To improve the reliability of the prediction results, an iterative calculation method is adopted in this embodiment. First, divide the preset period into several time steps, and within each time step, calculate the crack length at the next moment based on the current state. This step-by-step calculation method can more accurately reflect the non-linear characteristics of crack propagation, and at the same time is convenient for considering the changes in the stress state within each time period.

[0131] During the calculation process, it is also necessary to consider the critical conditions for crack propagation. When the calculated crack length exceeds the preset safety threshold, the system will automatically mark the corresponding time points, which can be used as important reference bases for equipment maintenance or replacement. At the same time, by calculating the derivative of the crack length with respect to time, the crack propagation rate can be obtained.

[0132] Exemplarily, historical data of crack propagation can be obtained to regularly detect the change of the crack length with time t. Use the least squares method to fit the material coefficient according to the crack prediction formula. Given the stress σ and the material coefficient k, predict the crack length at a future time point: ; Calculate the crack propagation speed, that is, the rate of change of the crack length with respect to time: .

[0133] Figure 2 Schematically shows a structural block diagram of a pump casing crack detection system for a single-casing slurry pump according to an embodiment of the present disclosure.

[0134] As Figure 2 shown, the pump casing crack detection system for a single-casing slurry pump includes: A target signal acquisition module, configured to acquire a target signal of a single-casing slurry pump, where the target signal is obtained by fusing detection signals of different modes; A crack area determination module, configured to determine a crack area of the single-casing slurry pump according to the target signal; A pump casing crack detection module, configured to construct a crack model according to the crack area, so as to periodically detect a crack in the pump casing of the single-casing slurry pump through the crack model.

[0135] Based on the above embodiments, as an optional embodiment, the target signal acquisition module is further configured to acquire an electromagnetic signal collected by an electromagnetic induction sensor disposed on a key area of the single-casing slurry pump; acquire an ultrasonic signal collected by an ultrasonic sensor disposed on the key area of the single-casing slurry pump; and fuse the electromagnetic signal and the ultrasonic signal to obtain a target signal.

[0136] Based on the above embodiments, as an optional embodiment, the target signal acquisition module is further configured to respectively determine signal-to-noise ratios of the electromagnetic signal and the ultrasonic signal; perform weighted summation on the electromagnetic signal and the ultrasonic signal according to the signal-to-noise ratios to obtain a target signal.

[0137] Based on the above embodiments, as an optional embodiment, the target signal acquisition module is further configured to extract high-frequency components and low-frequency components of the target signal, where the low-frequency components characterize the characteristics of cracks in the single-casing slurry pump; perform denoising processing on the high-frequency components; and reconstruct the denoised high-frequency components and the low-frequency components to obtain a filtered target signal.

[0138] Based on the above embodiments, as an optional embodiment, the crack area determination module is further configured to determine a crack center based on extraction of a magnetic field change of the electromagnetic signal; determine a crack depth through a reflection time difference and amplitude attenuation of the ultrasonic signal; determine a crack width according to an edge feature of the target signal; and determine a crack area according to the crack center, the crack depth, and the crack width.

[0139] Based on the above embodiments, as an optional embodiment, the crack area determination module is further configured to acquire a flow velocity gradient, a stress influence, and material wear of the single-casing slurry pump; calculate a crack propagation correction amount based on the flow velocity gradient, the stress influence, and the material wear of the single-casing slurry pump; and correct the crack area based on the crack propagation correction amount.

[0140] Based on the above embodiments, as an alternative embodiment, the pump housing crack detection module is further configured to extract the point cloud data of the crack region; fit the point cloud data to obtain a crack model; establish a crack prediction formula based on the crack model, and the crack prediction formula is used to characterize the evolution law of the cracks on the surface of the single-housing slurry pump pump housing over time. Determine the crack length within a preset period according to the crack prediction formula.

[0141] According to embodiments of the present disclosure, any plurality of modules, sub-modules, units, and sub-units, or at least part of the functions of any of them can be implemented in one module. Any one or more of the modules, sub-modules, units, and sub-units according to embodiments of the present disclosure can be split into multiple modules for implementation. Any one or more of the modules, sub-modules, units, and sub-units according to embodiments of the present disclosure can be at least partially implemented as a hardware circuit, such as a field-programmable gate array (FPGA), a programmable logic array (PLA), a system-on-chip, a system-on-substrate, a system-on-package, an application-specific integrated circuit (ASIC), or can be implemented by any other reasonable means of integrating or packaging circuits, or in any one of the three implementation manners of software, hardware, and firmware, or in any appropriate combination of several of them. Alternatively, one or more of the modules, sub-modules, units, and sub-units according to embodiments of the present disclosure can be at least partially implemented as a computer program module, and when the computer program module is run, it can execute the corresponding functions.

[0142] For example, any plurality of the target signal acquisition module, the crack region determination module, and the pump housing crack detection module can be combined and implemented in one module / unit / sub-unit, or any one of the modules / units / sub-units can be split into multiple modules / units / sub-units. Alternatively, at least part of the functions of one or more of these modules / units / sub-units can be combined with at least part of the functions of other modules / units / sub-units and implemented in one module / unit / sub-unit. According to embodiments of the present disclosure, at least one of the target signal acquisition module, the crack region determination module, and the pump housing crack detection module can be at least partially implemented as a hardware circuit, such as a field-programmable gate array (FPGA), a programmable logic array (PLA), a system-on-chip, a system-on-substrate, a system-on-package, an application-specific integrated circuit (ASIC), or can be implemented by any other reasonable means of integrating or packaging circuits, or in any one of the three implementation manners of software, hardware, and firmware, or in any appropriate combination of several of them. Alternatively, at least one of the own target signal acquisition module, the crack region determination module, and the pump housing crack detection module can be at least partially implemented as a computer program module, and when the computer program module is run, it can execute the corresponding functions.

[0143] It should be noted that the pump casing crack detection system part of the single-casing slurry pump in the embodiments of the present disclosure corresponds to the pump casing crack detection method part of the single-casing slurry pump in the embodiments of the present disclosure. For the description of the pump casing crack detection system part of the single-casing slurry pump, please specifically refer to the data processing method part, and it will not be elaborated here.

[0144] Figure 3 A block diagram of an electronic device suitable for implementing the method described above according to an embodiment of the present disclosure is schematically shown. Figure 3 The electronic device shown is merely an example and should not impose any limitation on the functions and usage scope of the embodiments of the present disclosure.

[0145] As Figure 3 shown, the electronic device 300 according to an embodiment of the present disclosure includes a processor 301, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 302 or the program loaded from the storage section 308 into the random access memory (RAM) 303. The processor 301 may include, for example, a general microprocessor (such as a CPU), an instruction set processor, and / or a related chipset, and / or a dedicated microprocessor (such as an application specific integrated circuit (ASIC)), and so on. The processor 301 may also include on-board memory for caching purposes. The processor 301 may include a single processing unit or multiple processing units for performing different actions of the method flow according to the embodiments of the present disclosure.

[0146] In the RAM 303, various programs and data required for the operation of the electronic device 300 are stored. The processor 301, the ROM 302, and the RAM 303 are connected to each other through a bus 304. The processor 301 performs various operations of the method flow according to the embodiments of the present disclosure by executing the programs in the ROM 302 and / or the RAM 303. It should be noted that the program may also be stored in one or more memories other than the ROM 302 and the RAM 303. The processor 301 may also perform various operations of the method flow according to the embodiments of the present disclosure by executing the programs stored in the one or more memories.

[0147] According to an embodiment of the present disclosure, the electronic device 300 may further include an input / output (I / O) interface 305, and the input / output (I / O) interface 305 is also connected to the bus 304. The system 300 may further include one or more of the following components connected to the input / output (I / O) interface 305: an input portion 306 including a keyboard, a mouse, etc.; an output portion 307 including, for example, a cathode ray tube (CRT), a liquid crystal display (LCD), etc. and a speaker, etc.; a storage portion 308 including a hard disk, etc.; and a communication portion 309 including a network interface card such as a LAN card, a modem, etc. The communication portion 309 performs communication processing via a network such as the Internet. The drive 310 is also connected to the input / output (I / O) interface 305 as needed. A removable medium 311, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 310 as needed so that a computer program read from it can be installed into the storage portion 308 as needed.

[0148] According to an embodiment of the present disclosure, the method flow according to the embodiment of the present disclosure may be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable storage medium, and the computer program includes program codes for executing the method shown in the flowchart. In such an embodiment, the computer program may be downloaded and installed from the network through the communication portion 309, and / or installed from the removable medium 311. When the computer program is executed by the processor 301, the above functions defined in the system of the embodiment of the present disclosure are executed. According to an embodiment of the present disclosure, the above-described systems, devices, apparatuses, modules, units, etc. may be implemented by computer program modules.

[0149] The present disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or may exist separately without being assembled into the device / apparatus / system. The above computer-readable storage medium carries one or more programs, and when the above one or more programs are executed, the method according to the embodiment of the present disclosure is implemented.

[0150] According to an embodiment of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium. For example, it may include but is not limited to: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In the present disclosure, the computer-readable storage medium may be any tangible medium that contains or stores a program, and the program can be used by or in combination with an instruction execution system, apparatus, or device.

[0151] For example, according to an embodiment of the present disclosure, the computer-readable storage medium may include one or more memories other than the above-described ROM 302 and / or RAM 303 and / or ROM 302 and RAM 303.

[0152] An embodiment of the present disclosure also includes a computer program product, which includes a computer program that contains program code for executing the method provided by the embodiment of the present disclosure. When the computer program product runs on an electronic device, the program code is used to cause the electronic device to implement the method provided by the embodiment of the present disclosure.

[0153] When the computer program is executed by the processor 301, the above functions defined in the system / apparatus of the embodiment of the present disclosure are executed. According to an embodiment of the present disclosure, the above-described systems, apparatuses, modules, units, etc. may be implemented by computer program modules.

[0154] In one embodiment, the computer program may rely on tangible storage media such as optical storage devices, magnetic storage devices, etc. In another embodiment, the computer program may also be transmitted and distributed in the form of a signal on a network medium, and downloaded and installed through the communication part 309, and / or installed from the removable medium 311. The program code contained in the computer program may be transmitted by any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0155] According to embodiments of the present disclosure, program code for executing the computer programs provided by the embodiments of the present disclosure can be written in any combination of one or more programming languages. Specifically, these computing programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages include, but are not limited to, such as Java, C++, Python, the "C" language, or similar programming languages. The program code can be executed entirely on the user's computing device, partially on the user's device, partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device can be connected to the user's computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (e.g., by connecting through the Internet using an Internet service provider).

[0156] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram can represent a module, a program segment, or a part of code that contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks can occur in a different order than marked in the accompanying drawings. For example, two consecutive blocks shown can actually be executed substantially in parallel, and they can sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram or flowchart, and combinations of blocks in the block diagram or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions. Those skilled in the art can understand that the features recited in the various embodiments and / or claims of the present disclosure can be combined and / or combined in various ways, even if such combinations or combinations are not explicitly recited in the present disclosure. In particular, without departing from the spirit and teachings of the present disclosure, the features recited in the various embodiments and / or claims of the present disclosure can be combined and / or combined in various ways. All such combinations and / or combinations fall within the scope of the present disclosure.

[0157] The above describes the embodiments of the present disclosure. However, these embodiments are for illustrative purposes only and are not intended to limit the scope of the present disclosure. Although the embodiments are described separately above, this does not mean that the measures in each embodiment cannot be used advantageously in combination. The scope of the present disclosure is defined by the appended claims and their equivalents. Without departing from the scope of the present disclosure, those skilled in the art can make various substitutions and modifications, and all such substitutions and modifications should fall within the scope of the present disclosure.

Claims

1. A method for detecting cracks in a pump casing of a single-casing slurry pump, characterized in that: include: Acquire a target signal of a single-casing slurry pump, wherein the target signal is obtained by fusing detection signals of different modes; determining a crack region of the single-casing slurry pump according to the target signal; A crack model is constructed according to the crack area, so as to detect cracks in the pump casing of the single-casing slurry pump through the crack model.

2. The method according to claim 1, characterized in that The obtaining of the target signal of the single casing slurry pump comprises: Acquire electromagnetic signals collected by electromagnetic induction sensors installed on key areas of the single-shell slurry pump; Acquire ultrasonic signals collected by ultrasonic sensors arranged on key areas of the single-casing slurry pump; The electromagnetic signal and the ultrasonic signal are fused to obtain a target signal.

3. The method according to claim 2, characterized in that The fusing the electromagnetic signal and the ultrasonic signal to obtain a target signal comprises: determining the signal-to-noise ratio of the electromagnetic signal and the ultrasonic signal respectively; The electromagnetic signal and the ultrasonic signal are weightedly summed according to the signal-to-noise ratio to obtain a target signal.

4. The method according to claim 1, characterized in that: After obtaining the target signal of the single-casing slurry pump, the method further includes: Extracting a high-frequency component and a low-frequency component of the target signal, wherein the low-frequency component represents the characteristics of the cracks in the single-shell slurry pump; Performing denoising on the high frequency component; The denoised high-frequency component and the low-frequency component are reconstructed to obtain a filtered target signal.

5. The method according to claim 1, characterized in that The detection signal includes an electromagnetic signal and an ultrasonic signal, and determining the crack area of ​​the single-shell slurry pump according to the target signal includes: Determine the crack center based on the magnetic field change extraction of the electromagnetic signal; Determining the crack depth by the reflection time difference and amplitude attenuation of the ultrasonic signal; Determining the crack width according to the edge characteristics of the target signal; The crack area is determined according to the crack center, the crack depth and the crack width.

6. The method according to claim 5, characterized in that The method further comprises: Obtaining the flow velocity gradient, stress influence and material wear of the single casing slurry pump; Calculating a crack expansion correction amount based on the flow velocity gradient, stress influence, and material wear of the single-casing slurry pump; The crack region is corrected based on the crack extension correction amount.

7. The method according to claim 1, characterized in that The method of constructing a crack model according to the crack area to periodically detect cracks in the pump casing of the single-casing slurry pump through the crack model includes: Extracting point cloud data of the crack area; Fitting the point cloud data to obtain a crack model; A crack prediction formula is established based on the crack model, and the crack prediction formula is used to characterize the evolution law of cracks on the surface of the pump casing of a single-casing slurry pump over time; The crack length within a preset period is determined according to the crack prediction formula.

8. A pump casing crack detection system for a single-casing slurry pump, characterized in that: include: A target signal acquisition module is used to acquire a target signal of a single-casing slurry pump, wherein the target signal is obtained by fusing detection signals of different modes; A crack region determination module, used for determining the crack region of the single-casing slurry pump according to the target signal; A pump casing crack detection module is used to construct a crack model according to the crack area, so as to perform periodic detection on the pump casing crack of the single-casing slurry pump through the crack model.

9. An electronic device, characterized in that: include: one or more processors; a memory for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: Executable instructions are stored thereon, and when the instructions are executed by a processor, the processor implements the method according to any one of claims 1 to 7.

Images