Ai-based ultrasonic cleaning control and predictive maintenance system for valve body, and method thereof

Abstract

A method and system for ultrasonic cleaning of a valve body are disclosed. A method performed by an ultrasonic cleaner according to one embodiment of the present disclosure may include: a step of obtaining first information related to the cleaning water of the ultrasonic cleaner, an airflow rate of a first space where the valve body is located, and a frequency wavelength of the diaphragm of the ultrasonic cleaner; a step of i) inputting the first information, the airflow rate, and the frequency wavelength and ii) second information related to the valve body into a first artificial intelligence (AI) model to obtain a first value indicating the possibility of an abnormality of the ultrasonic cleaner; a step of classifying whether the cause of the possibility of an abnormality is a performance degradation of the diaphragm through the first AI model when the first value is greater than or equal to a first threshold value; and a step of transmitting a first message requesting maintenance of the ultrasonic cleaner to a first terminal device used by an administrator based on the classification that the cause of the possibility of an abnormality is a performance degradation of the diaphragm.

Description

Technology Field

[0001] The present disclosure relates to valve body control technology, and more specifically, to an artificial intelligence-based valve body ultrasonic cleaning control and predictive maintenance system and method. Background Technology

[0003] The valve body applied to an automobile's engine control system is primarily made of aluminum and has complex flow paths and fine holes formed inside.

[0004] During the machining process of such valve bodies, fine chips or foreign substances are inevitably generated, and to remove them, a deburring process using fine balls made of steel or stainless steel (SUS) is performed.

[0005] However, if the finished vehicle is shipped with machining chips or deburring balls remaining inside the valve body, it may cause the engine control valve to seize while driving, leading to fatal consequences such as vehicle stoppage or injury.

[0006] Therefore, in valve body production lines, it is essential to ensure perfect cleanliness where no foreign substances are allowed to prevent massive economic and reliability losses for the manufacturer. The problem to be solved

[0008] The purpose of the present disclosure is to provide an artificial intelligence-based valve body ultrasonic cleaning control and predictive maintenance system and method.

[0009] The problems that this disclosure aims to solve are not limited to those mentioned above, and other unmentioned problems will be clearly understood by a person skilled in the art from the description below. means of solving the problem

[0011] A method for cleaning a valve body performed by an ultrasonic cleaner according to one embodiment of the present disclosure comprises: a step of obtaining first information related to the cleaning water of the ultrasonic cleaner, an airflow rate of a first space where the valve body is located, and a frequency wavelength of the diaphragm of the ultrasonic cleaner; a step of i) inputting the first information, the airflow rate, and the frequency wavelength and ii) second information related to the valve body into a first artificial intelligence (AI) model to obtain a first value indicating the possibility of an abnormality of the ultrasonic cleaner; a step of classifying whether the cause of the possibility of an abnormality is a performance degradation of the diaphragm through the first AI model when the first value is greater than or equal to a first threshold value; and a step of transmitting a first message requesting maintenance of the ultrasonic cleaner to a first terminal device used by an administrator based on the classification that the cause of the possibility of an abnormality is a performance degradation of the diaphragm, wherein the first information includes the temperature and water level of the cleaning water, and the second information may include the cleaning conditions of the valve body.

[0012] And, the above method may further include the step of controlling the operation of the ultrasonic cleaner such that the first information and the airflow value of the first space satisfy the cleaning conditions of the valve body, based on the fact that the first value is greater than or equal to a first threshold and the cause of the possibility of anomaly is classified not as a performance degradation of the diaphragm; and the step of inputting the controlled first information and the airflow value of the first space back into the first AI model to determine whether the first value is less than the first threshold.

[0013] And, the above method may further include the step of performing a cleaning operation on the valve body in the first space based on the first information and the frequency wavelength, based on the first value being less than the first threshold value.

[0014] And, the first threshold value is determined by the ultrasonic cleaner based on the importance value of the valve body, and the importance value of the valve body can be determined based on at least one of the type of the valve body, the ultrasonic sensitivity of the valve body, or the price of the valve body.

[0015] And, the first AI model can be trained to: i) obtain a second value representing the correlation between the first information, the airflow and the frequency wavelength and ii) the cleaning conditions of the valve body; and apply a predefined first weight to the second value to obtain the first value.

[0016] And, the above method may further include the step of obtaining third information including three-dimensional position coordinates of metallic foreign matter remaining inside the valve body from an X-ray detector that transmits and inspects the valve body before the ultrasonic cleaner performs a cleaning operation on the valve body; and the step of performing beamforming cleaning by concentrating ultrasonic energy into a target area where the metallic foreign matter is located by individually controlling the phase of a driving signal applied to a plurality of ultrasonic vibration elements included in the diaphragm based on the obtained third information.

[0017] The above method may further include the steps of: collecting cleaning history data including unique identification information of the valve body, the calculated first value, applied cleaning conditions, and a classification result regarding whether the performance of the diaphragm has deteriorated, after a cleaning operation on the valve body is completed; encrypting the collected cleaning history data to generate a unique hash value; and generating a transaction to prove the cleanliness of the valve body and the soundness of the ultrasonic cleaner based on the generated hash value, and transmitting the transaction to a blockchain network composed of a plurality of nodes to record it in a distributed ledger. Effects of the invention

[0019] By various embodiments of the present disclosure, an artificial intelligence-based valve body ultrasonic cleaning control and predictive maintenance system and method may be provided.

[0020] According to various embodiments of the present disclosure, when removing fine chips inside an aluminum valve body, a more efficient cleaning operation can be performed by reducing variations in cleaning quality due to changes in environmental factors.

[0021] The effects of the present disclosure are not limited to those mentioned above, and other unmentioned effects will be clearly understood by a person skilled in the art from the description below. Brief explanation of the drawing

[0023] FIG. 1 is a drawing for illustrating an artificial intelligence-based valve body ultrasonic cleaning control and predictive maintenance system according to one embodiment of the present disclosure. FIG. 2 is a drawing for explaining the configuration of an ultrasonic cleaner according to one embodiment of the present disclosure. FIG. 3 is a flowchart for performing artificial intelligence-based valve body ultrasonic cleaning control and predictive maintenance operations according to one embodiment of the present disclosure. Specific details for implementing the invention

[0024] The advantages and features of the present disclosure and the methods for achieving them will become clear by referring to the embodiments described below in detail together with the accompanying drawings. However, the present disclosure is not limited to the embodiments disclosed below but may be implemented in various different forms. These embodiments are provided merely to ensure that the disclosure is complete and to fully inform those skilled in the art of the scope of the present disclosure, and the present disclosure is defined only by the scope of the claims.

[0025] The terms used herein are for describing the embodiments and are not intended to limit the disclosure. In this specification, the singular form includes the plural form unless specifically stated otherwise in the text. As used herein, "comprises" and / or "comprising" do not exclude the presence or addition of one or more other components in addition to the components mentioned.

[0026] Throughout the specification, the same reference numerals refer to the same components, and "and / or" includes each of the mentioned components and all combinations of one or more thereof. Although terms such as "first," "second," etc., are used to describe various components, they are not limited by these terms. These terms are used merely to distinguish one component from another. Accordingly, the first component mentioned below may be the second component within the technical scope of this disclosure.

[0027] Unless otherwise defined, all terms used herein (including technical and scientific terms) may be used in a meaning commonly understood by those skilled in the art to which this disclosure pertains. Additionally, terms defined in commonly used dictionaries are not to be interpreted ideally or excessively unless explicitly and specifically defined otherwise.

[0028] Spatially relative terms such as "below," "beneath," "lower," "above," and "upper" may be used to easily describe the relationship between one component and another, as illustrated in the drawings. Spatially relative terms should be understood as encompassing the different directions of the components during use or operation, in addition to the directions depicted in the drawings.

[0029] For example, if a component depicted in a drawing is inverted, a component described as being "below" or "beneath" another component may be placed "above" the other component. Therefore, the exemplary term "below" may encompass both the downward and upward directions. Components may also be oriented in other directions, and accordingly, spatially relative terms may be interpreted according to the orientation.

[0030] In describing the present disclosure, an artificial intelligence model may be composed of a plurality of neural network layers. Each of the plurality of neural network layers has a plurality of weight values ​​and performs neural network operations through operations between the results of operations of a previous layer and the plurality of weights. The plurality of weights possessed by the plurality of neural network layers may be optimized by the learning results of the artificial intelligence model. For example, the plurality of weights may be updated so that the loss value or cost value obtained from the artificial intelligence model during the learning process is reduced or minimized. The artificial neural network may include a Deep Neural Network (DNN), and examples include, but are not limited to, Convolutional Neural Networks (CNN), Deep Neural Networks (DNN), Recurrent Neural Networks (RNN), Restricted Boltzmann Machines (RBM), Deep Belief Networks (DBN), Bidirectional Recurrent Deep Neural Networks (BRDNN), or Deep Q-Networks.

[0031] Furthermore, blockchain is a general term for data tamper-proof technology based on distributed computing. In other words, blockchain refers to a distributed ledger technology in which transaction data authenticated by the consensus of P2P-connected nodes is stored in a distributed manner in blocks, and each block is linked together in a chain. With the recent advancement of blockchain-related technologies, there are attempts to solve problems in various fields by applying distributed ledger technology to them.

[0032] The following discloses an artificial intelligence-based valve body ultrasonic cleaning control and predictive maintenance system and method.

[0033] FIG. 1 is a diagram illustrating the configuration of an artificial intelligence-based valve body ultrasonic cleaning control and predictive maintenance system according to one embodiment of the present disclosure.

[0034] As illustrated in FIG. 1, the system (1000) may include an ultrasonic cleaner (100), a first terminal device (200) used by an administrator, and a second terminal device (300) used by a client.

[0035] Here, the manager is a general term for a person who controls the operation and function of the ultrasonic cleaner (100), and the client may be a general term for a person who requests the manager to clean a specific valve body. After receiving a request from the client to clean a specific valve body, the manager can perform a cleaning operation on the specific valve body through the ultrasonic cleaner (100).

[0036] FIG. 1 illustrates a case where there is only one orderer and one supplier, but is not limited thereto. The system (1000) may include terminal devices used by each of multiple orderers and multiple suppliers.

[0037] Here, each of the first terminal device (200) used by the administrator and the second terminal device (300) used by the client may be implemented as various types of devices (e.g., notebook, desktop, laptop, tablet PC, slate PC device, server device, etc.) and may also be implemented as a group of devices connected to one or more types of devices.

[0038] The ultrasonic cleaner (100) included in the system (1000), the first terminal device (200) used by the administrator, and the second terminal device (300) used by the client can communicate through a network. Here, the network may include a wired network and a wireless network. For example, the network may include various networks such as a Local Area Network (LAN), a Metropolitan Area Network (MAN), and a Wide Area Network (WAN).

[0039] Additionally, the network may include the known World Wide Web (WWW). However, the network according to the embodiments of the present disclosure is not limited to the networks listed above and may include at least a known wireless data network, a known telephone network, or a known wired or wireless television network.

[0040] An ultrasonic cleaner (100) can clean an object (e.g., a valve body) by converting high-frequency electrical energy generated from an oscillator into mechanical vibration energy through an ultrasonic vibrating plate (e.g., a vibrator) and radiating it into cleaning water.

[0041] Powerful ultrasonic vibrations passing through the cleaning water medium can continuously induce cavitation, a phenomenon in which numerous micro-vacuum bubbles are generated, contracted, and explode. At this time, the powerful micro-shock waves and high-temperature, high-pressure energy generated as the bubbles burst can physically and completely detach foreign substances deeply adhered not only to the surface of the object to be cleaned but also to minute crevices or complex internal structures that are difficult to see with the naked eye, thereby ensuring a high level of cleanliness.

[0042] The operation of the ultrasonic cleaner (100) and the control device (200) that controls it will be explained in detail with reference to FIGS. 2 and FIGS. 3.

[0043] FIG. 2 is a flowchart for explaining the configuration of an ultrasonic cleaner according to one embodiment of the present disclosure.

[0044] As illustrated in FIG. 2, the ultrasonic cleaner (100) may include a memory (110), a communication module (120), a display (130), an input module (140), and a processor (150).

[0045] However, the configuration illustrated in FIG. 2 is an illustrative diagram for implementing embodiments of the present disclosure, and appropriate hardware and software configurations that are obvious to a person skilled in the art may be additionally included in the ultrasonic cleaner (100) used by the administrator.

[0046] The memory (110) can store one or more instructions for the processor (150) to perform various operations. The memory (110) can store data supporting various functions of the ultrasonic cleaner (100) used by the manager, a program for the operation of the processor (150), and input / output data.

[0047] The memory (110) may include at least one type of storage medium among flash memory type, hard disk type, SSD type (Solid State Disk type), SSD type (Silicon Disk Drive type), multimedia card micro type, card type memory (e.g., SD or XD memory, etc.), RAM (random access memory; RAM), SRAM (static random access memory), ROM (read-only memory; ROM), EEPROM (electrically erasable programmable read-only memory), PROM (programmable read-only memory), magnetic memory, magnetic disk, and optical disk.

[0048] The communication module (120) may include one or more components including a circuit that enables communication with an external device. For example, the communication module (120) may include at least one of a broadcast receiving module, a wired communication module, a wireless communication module, a short-range communication module, and a location information module.

[0049] The display (130) displays (outputs) information processed in the ultrasonic cleaner (100) used by the manager. For example, the display (130) may display information on the execution screen of an application running in the ultrasonic cleaner (100) used by the manager, or UI (User Interface) and GUI (Graphic User Interface) information based on such execution screen information.

[0050] The input module (140) may include a device for receiving various data or / and interactions from an external device. For example, the input module (140) may include a touch panel, a keyboard, a mouse, etc.

[0051] The processor (150) can perform operations to control various modules and devices on the system by executing one or more instructions stored in memory (110). That is, the processor (150) can control the overall operation and function using each component of the ultrasonic cleaner (100) used by the manager.

[0052] Specifically, the processor (150) may be implemented as a memory that stores data for an algorithm or a program that reproduces the algorithm for controlling the operation of components within the ultrasonic cleaner (100) used by an administrator, and at least one processor that performs the aforementioned operation using the data stored in the memory. In this case, the memory and the processor may each be implemented as separate chips. Alternatively, the memory and the processor may be implemented as a single chip.

[0053] In addition, the processor (150) can control one or a combination of the components described above in order to implement various embodiments according to the present disclosure described in FIG. 3 below on the ultrasonic cleaner (100) used by the administrator.

[0054] Additionally or alternatively, although not illustrated in FIG. 2, the ultrasonic cleaner (100) may include one or more sensors (e.g., a wind direction sensor, a temperature sensor, a frequency measurement sensor, etc.).

[0055] FIG. 3 is a flowchart illustrating the operation of providing a platform for converting conversation text into order information according to one embodiment of the present disclosure.

[0056] The ultrasonic cleaner can obtain first information related to the cleaning water of the ultrasonic cleaner, the airflow of the first space where the valve body (i.e., the target valve body to be cleaned) is located, and the frequency wavelength of the vibrating plate of the ultrasonic cleaner (S310).

[0057] Specifically, the first information includes data on the current temperature and water level (amount) of the cleaning water used by the ultrasonic cleaner to clean fine foreign substances (e.g., machining chips and deburring balls made of steel or stainless steel (SUS) material) that may remain on the surface of the valve body and in the invisible inner diameter hole.

[0058] Here, the temperature and water level of the cleaning water are factors that directly affect the cavitation effect caused by ultrasound, and the airflow of the first space can be closely related to the drying efficiency and foreign matter scattering control before and after cleaning.

[0059] In order to precisely collect such multifaceted state data, as described above, the ultrasonic cleaner may include a sensor unit composed of a plurality of sensors.

[0060] In one example of the present disclosure, the sensor unit of the ultrasonic cleaner may include a temperature sensor for measuring the real-time temperature of the cleaning water, a water level sensor for detecting the amount of cleaning water loaded inside the cleaning tank, a wind direction or air volume sensor for measuring the air flow within the first space, and a frequency measuring sensor for measuring the wavelength, amplitude, or fine waveform change of the ultrasonic waves oscillating from the vibrating plate.

[0061] In this way, the first information, airflow, and frequency wavelength data obtained through the sensor unit can be input into the first AI model in the step to be described later and utilized as core basic data for inferring optimal cleaning conditions in real time and determining the predicted maintenance time of the diaphragm.

[0062] The ultrasonic cleaner can obtain a first value indicating the possibility of an abnormality in the ultrasonic cleaner by inputting i) first information, airflow and frequency wavelength and ii) second information related to the valve body into a first AI model (S320).

[0063] The ultrasonic cleaner can calculate and obtain a first value indicating the possibility of anomaly in the ultrasonic cleaner by inputting i) the first information (e.g., temperature and water level), the airflow of the first space, and the frequency wavelength of the vibrating plate, which are real-time status data obtained earlier, and ii) second information related to the target valve body, which is the object to be cleaned, into the first AI model.

[0064] Here, the second information may include the specific cleaning conditions of the target valve body required to achieve perfect cleanliness of the valve body (e.g., 100% removal of fine steel or stainless steel chips or deburring balls that can be inserted into the inner diameter hole of the valve body) (e.g., recommended temperature range, appropriate water level, required ultrasonic output profile, etc.). In this case, the second information may be transmitted from the second terminal device used by the client to the first terminal device and / or the ultrasonic cleaner.

[0065] The first AI model may be a pre-trained model based on machine learning or a deep neural network, and may be trained to analyze the multidimensional correlation between the input real-time state data and the second information, which is the target washing condition.

[0066] Specifically, the first AI model can be trained to calculate a first value by comprehensively considering the inconsistency of process conditions where currently measured environmental variables (e.g., temperature, water level, airflow, etc.) do not satisfy the cleaning conditions of the valve body, and the level of mechanical / electrical deterioration of the equipment itself based on noise or waveform distortion inherent in the frequency wavelength data of the diaphragm.

[0067] Specifically, the first AI model can be trained to infer the correlation between collected multi-type sensor data and target process conditions step by step.

[0068] For example, the first AI model can be trained to convert i) real-time physical quantity data consisting of first information (i.e., temperature, water level, etc.), airflow, and frequency wavelength of the diaphragm, and ii) ideal cleaning conditions (second information) required for perfect removal of foreign matter (chip) from the valve body into respective feature vectors, and to primarily obtain a second value representing the correlation between them.

[0069] Here, the second value may represent a degree of agreement or deviation score that quantifies how well the current cleaning environment and equipment condition conform to or deviate from the target cleaning conditions required by the valve body.

[0070] Furthermore, the first AI model can be trained to obtain a first value representing the possibility of failure and abnormality of the ultrasonic cleaner by applying a predefined first weight (e.g., multiplication operation or application of a non-linear function) to the second value calculated above.

[0071] At this time, the first weight may be a parameter that is differentially set according to the degree of influence each state data has on the fatal failure of the ultrasonic cleaner (e.g., burnout of the diaphragm) or the degradation of cleaning quality.

[0072] For example, minute deviations in temperature or airflow are assigned a relatively low weight because they can be overcome by simple environmental control, whereas deformation or attenuation of the frequency wavelength of the ultrasonic diaphragm, which directly affects the occurrence of cavitation, may be assigned a high weight as it is a precursor to failure directly linked to equipment aging.

[0073] Consequently, the first AI model can be trained to recognize a simple error between the current state and the target condition through the second value, and to determine through the first weight whether the error is due to simple environmental factors or a hardware defect such as an ultrasonic diaphragm (i.e., a target for predictive maintenance), thereby precisely deriving the final level of mechanical abnormality indications as the first value.

[0074] If the first value is greater than or equal to the first threshold value, the ultrasonic cleaner can classify whether the cause of the potential abnormality is the performance degradation of the diaphragm through the first AI model (S330).

[0075] In one example of the present disclosure, an ultrasonic cleaner primarily determines whether there is an abnormality in the ultrasonic cleaning process by comparing a calculated first value with a preset first threshold value.

[0076] If, as a result of the judgment, it is confirmed that the first value is greater than or equal to the first threshold value, the ultrasonic cleaner can perform a classification process to determine whether the root cause of the potential anomaly derived through the first AI model is due to performance degradation of the diaphragm (e.g., partial burnout of the vibrator, decrease in oscillation efficiency due to aging, etc.).

[0077] Specifically, even if a risk of cleaning failure is detected when a first value exceeds a first threshold, if the cause is merely temporary instability of the first information (temperature, water level) or airflow, the ultrasonic cleaner can return to a normal process by correcting the cleaning environment through a control mechanism to be described later.

[0078] Accordingly, the first AI model can be trained to extract and analyze mechanical / electrical defect features unique to the diaphragm, such as minute vibrations, the occurrence of abnormal harmonic noise, or continuous amplitude attenuation patterns, which are included specifically within the frequency wavelength data of the ultrasonic diaphragm among the entire input sensor data.

[0079] In one example of the present disclosure, the first AI model may be trained to additionally output an item-specific contribution value when the first value is greater than or equal to a first threshold.

[0080] Specifically, the first AI model can be trained to output a quantified output of how much each item used as input—namely, the first information (temperature, water level), the airflow, and the frequency wavelength data of the diaphragm—contributed to increasing the first value. The ultrasonic cleaner can identify the root cause of the currently occurring abnormal state by mutually comparing and analyzing the contribution values ​​for each item.

[0081] For example, if the contribution value for the frequency wavelength item of the ultrasonic cleaner's diaphragm is the highest compared to other items or exceeds a preset threshold among the contribution values ​​for each item, the cause of the current abnormality can be classified as performance degradation of the diaphragm (e.g., deterioration of the vibrator, waveform deformation due to partial burnout, etc.) rather than simple environmental factors.

[0082] Conversely, if the contribution value of the frequency wavelength is low but the contribution value of the first information (e.g., temperature, water level) or the airflow item is predominantly high, the ultrasonic cleaner may classify the cause of the abnormality as a temporary discrepancy in the environmental setting value.

[0083] In this way, by configuring the calculation and analysis of item-specific contribution values ​​that are triggered when a first threshold is exceeded, the present disclosure can reliably identify accurate hardware targets requiring predictive maintenance, going beyond the simple detection of abnormal signs.

[0084] Based on the classification that the cause of the potential abnormality is the performance degradation of the diaphragm, the ultrasonic cleaner can transmit a first message requesting maintenance of the ultrasonic cleaner to a first terminal device used by an administrator (S340).

[0085] Based on the final classification of the cause of potential abnormalities as the degradation of the mechanical / electrical performance of the ultrasonic diaphragm (e.g., deterioration of the transducer, partial burnout of the frequency oscillation unit, etc.) through an analysis of contribution figures by item, a predictive maintenance process can be initiated for the ultrasonic cleaner.

[0086] Specifically, the ultrasonic cleaner can generate a first message requesting maintenance of the ultrasonic cleaner in advance before the production line stops operating due to a complete failure of the diaphragm, and transmit this to a first terminal device used by a process manager via a communication network.

[0087] Here, the first message may include not only a simple suspected fault alarm, but also specific diagnostic data to support the manager's rapid and accurate decision-making.

[0088] In one embodiment, the first message may include information regarding the current frequency attenuation level of the diaphragm analyzed by the first AI model, the expected remaining useful life (RUL) of the diaphragm, the exact location or identification information of the vibrator requiring maintenance, and the probability (risk of cleanliness degradation) that a microchip inside the target valve body will not be removed if no action is taken.

[0089] With this configuration, managers can prevent fatal accidents caused by the mass production of defective cleaning products and, at the same time, establish an optimal maintenance schedule that minimizes line downtime, thereby taking preemptive measures such as replacing diaphragms.

[0090] In one example of the present disclosure, if the calculated first value is greater than or equal to a preset first threshold value and / or if the cause of the possibility of such an anomalous value is classified through the analysis of the contribution values ​​for each item described above as being a simple environmental factor (e.g., temporary deviation of cleaning water temperature, water level, or airflow) rather than a degradation of the mechanical performance of the ultrasonic diaphragm, the ultrasonic cleaner may perform a feedback control step of automatically adjusting the operation of the ultrasonic cleaner to satisfy the target cleaning conditions of the valve body.

[0091] Specifically, the ultrasonic cleaner can operate actuators such as a heating heater, a water supply and drainage pump, or / and a blower fan for drying / stirring to correct the first information (temperature and water level) and the airflow value of the first space to the optimal target value required by the valve body (e.g., a value related to the cleaning conditions of the valve body).

[0092] Subsequently, the ultrasonic cleaner acquires sensor data representing the adjusted first information and airflow values ​​again and inputs them into the first AI model to secondarily determine whether the newly calculated first value has decreased below the first threshold value and entered a stable range. Through this closed-loop self-correction mechanism, the present invention can restore an optimal cleaning environment in real time without manual intervention by an operator.

[0093] Subsequently, based on the re-entered data, if the first value is calculated to be less than the first threshold value—that is, if it is verified that the possibility of an abnormality in the cleaning process is completely eliminated and perfect cleanliness can be secured—the ultrasonic cleaner can perform the main cleaning operation on the valve body loaded in the first space based on the adjusted first information and the frequency wavelength.

[0094] This can provide an excellent effect of fundamentally blocking the production of defective valve bodies containing residual microchips by optimizing and verifying environmental factors 100% through artificial intelligence during the preliminary stage before entering the main process.

[0095] Meanwhile, the first value may represent an abnormal score (e.g., a value between 0 and 100 or a percentage probability) that quantifies the probability that the current cleaning process deviates from the normal course, resulting in defective products or equipment failure.

[0096] In other words, the higher the first value is calculated, the more difficult it is to completely remove metallic foreign substances adhered to the valve body with the current state of the cleaning water or the output state of the ultrasonic vibrating plate, or it indicates that a state requiring repair of the ultrasonic cleaner itself is imminent.

[0097] According to one embodiment of the present disclosure, the first threshold value, which determines whether there is an abnormality in the ultrasonic cleaner and serves as a judgment criterion for the first AI model, is not a fixed constant but can be dynamically determined and varied by the ultrasonic cleaner (or / and the first terminal device used by the manager) based on the importance value of the valve body, which is the object to be cleaned.

[0098] Here, the importance value of the valve body can be comprehensively calculated based on at least one of the following parameters: the 'Type' of the valve body, which indicates the complexity of the internally formed flow path and the difficulty of chip removal; the 'Ultrasonic Sensitivity,' which indicates the risk of surface damage or deformation due to ultrasonic cavitation impact; or the 'Price (Unit Price)' of the valve body, which indicates the economic loss and recall risk resulting from defective shipment.

[0099] For example, in the case of a type that includes an expensive precision control valve body or a thin bulkhead structure vulnerable to ultrasonic shock, the importance value is set / calculated / defined relatively high, and inversely proportional to this, the first threshold value can be set / calculated / defined more strictly (i.e., to a lower value).

[0100] The process of dynamically determining the first threshold value by calculating the importance value of the valve body is as follows.

[0101] In one embodiment, when a valve body is introduced into a first space, the ultrasonic cleaner can obtain unique identification information of a target valve body by scanning an identification tag (e.g., barcode, QR code, RFID, etc.) attached to the valve body or a transport jig, or by receiving production instruction data from an external Manufacturing Execution System (MES).

[0102] The ultrasonic cleaner can query a database based on acquired unique identification information to collect parameters (e.g., type of valve body, ultrasonic sensitivity, price, etc.) for calculating the importance value of the corresponding valve body. Here, these parameters can be quantified into objective quantitative indicators. Furthermore, based on these parameters, the ultrasonic cleaner can obtain a complexity index, an ultrasonic sensitivity index, and an economic risk.

[0103] First, the complexity index according to the 'type' of the valve body can be scored by an ultrasonic cleaner in inverse proportion to geometric values ​​such as the number of bends in the internal flow path, the depth of the blind hole, and / or the minimum inner diameter where machining chips are likely to stick, which are extracted from the 3D CAD design data of the part.

[0104] Secondly, the 'ultrasonic sensitivity' indicator can be quantified by an ultrasonic cleaner as the probability of risk of micro-cracks or deformation occurring due to powerful ultrasonic cavitation shock waves, based on the material grade (strength) of the aluminum alloy constituting the valve body or the minimum thickness information of the internal bulkhead.

[0105] Thirdly, the 'price' indicator may be a value normalized by an ultrasonic cleaner for economic risks such as the manufacturing cost of the valve body, the class of the vehicle in which it is installed (e.g., standard vehicle vs. luxury / high-performance vehicle), or recall costs incurred due to past and foreign matter defects.

[0106] The ultrasonic cleaner can derive the final importance value by applying individual weights, which are pre-assigned according to the production line policy, to each of the collected complexity indicators, ultrasonic sensitivity indicators, and economic risk indicators, and by performing a weighted sum operation.

[0107] For example, an ultrasonic cleaner can obtain a first intermediate value by applying a second weight to the complexity index, obtain a second intermediate value by applying a third weight to the ultrasonic sensitivity index, and obtain a third intermediate value by applying a fourth weight to the economic risk index. Additionally, the ultrasonic cleaner can obtain an importance value by summing the first intermediate value, the second intermediate value, and the third intermediate value.

[0108] For example, in the case of a high-performance valve body that is difficult to clean due to its extremely complex internal flow path and the presence of fine baffles, and which causes fatal engine defects when a failure occurs, the highest level of importance can be calculated as a result of the weighted sum of each of the above indicators.

[0109] The higher the calculated importance value, the more the ultrasonic cleaner can be controlled so that the first threshold value, which is the baseline for the first AI model to detect abnormalities, is lowered (i.e., strictly set), thereby triggering the immediate control correction and predictive maintenance process (S330, S340) with only very minute fluctuations in the cleaning environment or initial noise signs of the diaphragm.

[0110] Through this, the present disclosure can intelligently perform customized, defect-free cleaning quality control and equipment life management optimized for the characteristics of each part, even in multi-product mixed production lines.

[0111] According to another embodiment of the present disclosure, the ultrasonic cleaning system may further include multi-modal sensor fusion and phased array control technology that is organically linked with an X-ray detection process.

[0112] Specifically, before the ultrasonic cleaner performs the main cleaning operation on the valve body, the ultrasonic cleaner can obtain third information from an X-ray detection system that performs a pre-transmission inspection of the valve body.

[0113] Here, the third information may include three-dimensional positional coordinate data of metallic foreign matter (e.g., 1.2 phi ball-shaped chips made of steel or / and stainless steel (SUS) introduced during the deburring process) that remains inserted into an invisible corner or deep inner hole of the valve body.

[0114] The ultrasonic cleaner can input the acquired third information (e.g., 3D position coordinates) as an additional environmental variable to the first AI model, or precisely map the target zone in 3D space where the foreign substance is adhered through a separate phase calculation module.

[0115] Next, instead of radiating uniform ultrasound to the entire cleaning tank, the ultrasonic cleaner can perform beamforming control to maximize ultrasonic cavitation energy in the target area.

[0116] To this end, the ultrasonic diaphragm may be composed of multiple ultrasonic vibration elements arranged in a multi-array, and the control unit may individually adjust the phase delay time and amplitude of the high-frequency driving signal applied to each vibration element to induce the ultrasonic waves to cause constructive interference in the target area.

[0117] Through this X-ray data-based ultrasonic beamforming cleaning configuration, the present disclosure can efficiently remove critical foreign substances that are strongly embedded in complex and narrow blind holes inside an aluminum valve body and are difficult to detach with general overall cleaning by locally striking them strongly.

[0118] Furthermore, it can provide an excellent effect that can drastically prevent side effects such as erosion of the surface of the aluminum valve body or micro-deformation caused by excessive ultrasonic energy being applied for a long time to unnecessary normal areas where no foreign substances exist.

[0119] According to another embodiment of the present disclosure, the ultrasonic cleaning method described above may further include a configuration linked with a blockchain network to ensure data integrity regarding the cleaning quality and equipment status of the valve body and to ensure traceability.

[0120] Even a single tiny steel ball or machined chip of a specific size remaining in the internal air pocket of a vehicle's engine control valve body can cause fatal accidents, such as engine stalling while driving.

[0121] Therefore, a quality certification system may be essential to clarify liability and prove the process integrity of the parts manufacturer when vehicle defects occur after the vehicle is delivered or in the future.

[0122] To this end, the ultrasonic cleaner can acquire or / and identify unique identification information (e.g., serial number, barcode, QR code, or RFID tag value) assigned to the valve body immediately after the ultrasonic cleaning process for the target valve body is completed.

[0123] In addition, the ultrasonic cleaner can generate cleaning history data by packaging together the cleaning conditions acquired and controlled at the time of cleaning (the first information and airflow), the first numerical value calculated by the first AI model (anomaly score), and the soundness status of the diaphragm classified at that time (i.e., there were no signs of performance degradation or failure).

[0124] Subsequently, the ultrasonic cleaner can apply a hash algorithm (e.g., SHA-256) to the generated cleaning history data to produce a unique encrypted hash value, generate a data transaction containing this value, and transmit it to an external blockchain network.

[0125] The cleaning history data recorded in the distributed ledger through the consensus algorithm of multiple distributed nodes constituting the blockchain network can be fundamentally impossible to tamper with or delete after the fact.

[0126] Through this blockchain integration configuration, if a message raising suspicions of a part defect is transmitted from a terminal device used by a vehicle manufacturer or consumer in the future, the terminal device used by the manufacturer of the valve body can provide an immutable digital quality guarantee certificate to the vehicle manufacturer or consumer, proving that the valve body was cleaned under optimal water level and temperature conditions verified by AI in a diaphragm-free state.

[0127] Here, the digital quality assurance certificate (i.e., cleaning history transaction) may include cleaning history data recorded on a blockchain distributed ledger, making it permanently impossible to tamper with.

[0128] This can maximize the external credibility of the parts manufacturing process and produce excellent effects in preemptively defending against massive economic losses caused by unfair recalls or claims.

[0129] Meanwhile, the disclosed embodiments may be implemented in the form of a recording medium that stores instructions executable by a computer. The instructions may be stored in the form of program code and, when executed by a processor, may generate a program module to perform the operation of the disclosed embodiments. The recording medium may be implemented as a computer-readable recording medium.

[0130] Computer-readable recording media include all types of recording media that store instructions that can be decoded by a computer. Examples include ROM (Read Only Memory), RAM (Random Access Memory), magnetic tape, magnetic disk, flash memory, optical data storage devices, etc.

[0131] As described above, the disclosed embodiments have been explained with reference to the attached drawings. Those skilled in the art will understand that the present disclosure may be practiced in forms different from the disclosed embodiments without changing the technical spirit or essential features of the present disclosure. The disclosed embodiments are illustrative and should not be interpreted restrictively.

Claims

Claim 1 A method for ultrasonically cleaning a valve body, performed by an ultrasonic cleaner, wherein the method comprises: a step of obtaining real-time measurement data by measuring in real-time first information related to the cleaning water of the ultrasonic cleaner, the airflow of a first space where the valve body is located, and the frequency wavelength of the diaphragm of the ultrasonic cleaner; a step of calculating a deviation score indicating whether the current cleaning environment and equipment state correspond to the cleaning conditions by comparing the obtained real-time measurement data with preset cleaning conditions of the valve body; a step of deriving a final abnormality probability index of the ultrasonic cleaner by applying a preset first weight to the calculated deviation score, wherein the first weight is differentially set and applied higher to the item of deformation or attenuation of the frequency wavelength of the diaphragm than to the item of airflow of the first space; and a step of determining whether the cause of the abnormality of the ultrasonic cleaner is a performance degradation of the diaphragm based on the contribution value of the item of deformation of the frequency wavelength among the real-time measurement data that contributed to the rise of the final abnormality probability index when the derived final abnormality probability index is greater than or equal to a preset threshold. A method comprising the step of transmitting a first message requesting maintenance of the ultrasonic cleaner to a first terminal device used by an administrator based on the determination that the cause of the above abnormality is performance degradation of the diaphragm, wherein the first information includes the temperature and level of the cleaning water, and the threshold value is dynamically determined by the ultrasonic cleaner according to an importance value of the valve body calculated based on at least one of the type of the valve body, the ultrasonic sensitivity of the valve body, or the price of the valve body. Claim 2 delete Claim 3 delete Claim 4 delete Claim 5 delete

Images