METHOD FOR VERIFYING THE ASSEMBLY OF CONNECTORS IN BATTERY PACKS

Abstract

Method for checking the assembly of a connector, wherein the method comprises capturing at least one audio signal from the area of ​​an assembly line during the assembly of a connector and includes checking the assembly of a connector on the basis of the at least one audio signal.

Description

INTRODUCTION

[0001] The information contained in this section is intended to provide a general context for the disclosure. Work by the inventors identified herein, to the extent described in this section, as well as aspects of the description that may not be prior art at the time of filing, are neither expressly nor impliedly acknowledged as prior art over the present disclosure.

[0002] The present disclosure relates to assembly lines and, in particular, to a system and / or method for checking the correct assembly of a connector, e.g., in battery packaging.

[0003] Cooling hoses are essential components of battery electric vehicles (BEVs) because they play a critical role in controlling the thermal performance of the vehicle's battery pack and other critical components. However, after the battery pack is assembled, accessing or replacing battery pack cooling components can be difficult. Therefore, it is important to perform inline quality control to ensure flawless battery pack assembly.

[0004] The cooling hose can be assembled using one or more connectors, such as quick connectors (QC). The connectors can be manually connected by an operator, and the correct engagement of the connectors can be verified visually by the operator or another person along the assembly line. However, it can be difficult to verify the correct fit of the connectors with the naked eye, as the dimensions of each connector can be small (e.g., approximately 10 mm).

[0005] WO 2020 170 212 A1 relates to a monitoring and inspection system for a work area, comprising a non-visual sensory detection sensor, such as a microphone or vibration detection sensor, and a processor. The sensor is configured to detect noise or vibration generated in the work area and received by the processor. The processor analyzes the received acoustic and / or vibratory signals and compares the received signals with an expected signal to verify whether the acoustic and / or vibration signature of the detected signal is an acoustic and / or vibration signature associated with the operational step performed to confirm that the operational step was performed and that it was performed properly.

[0006] US 2017 0 092 099 A1 relates to a method for confirming the connection between two or more components. The method includes receiving acoustic data from the connection between two or more components at a microphone, the microphone being worn by a user, determining whether a predetermined acoustic signature is included in the received acoustic data, and generating a connection status signal based on the determination of whether the predetermined acoustic signature is included in the received acoustic data.

[0007] EP 3 871 928 A1 relates to a device for testing the connection of components by a gripper, wherein the connection of two or more components generates a connection noise. The device comprises a plurality of audio sensors, a fastening element for fastening the plurality of audio sensors at different positions on the gripper, and a control unit. The control unit comprises an input for receiving the audio signals from the audio sensors, a neural network for isolating the connection noise from the audio signals received by the audio sensors using independent component analysis based on training audio data obtained from audio signals produced during a plurality of training connections in a controlled environment, and an output for indicating a desired connection status based on the isolated connection noise. SUMMARY

[0008] The invention relates to a method for testing the assembly of a connecting piece.

[0009] According to the invention, the method comprises detecting at least one audio signal from the area of ​​an assembly line during the assembly of the connector, detecting a relative position of an operator and an audio sensor unit within the area, wherein the audio sensor unit is configured to detect the at least one audio signal, and checking the assembly of the connector on the basis of the at least one audio signal.

[0010] In some example embodiments, the testing verifies the assembly in real time while an electric vehicle battery including the connector is being assembled on the assembly line.

[0011] In some example embodiments, detecting the relative position includes detecting a position of the operator within the range, determining whether the position of the operator is in line with a position of the audio sensor unit, and moving the audio sensor unit toward the position of the operator in response to determining that the position of the operator is not in line with the position of the audio sensor unit.

[0012] In some example embodiments, detecting the position of the operator includes continuously detecting the position of the operator.

[0013] In some example embodiments, determining whether the position of the operator is in line with a position of the audio sensor unit includes calculating the offset for the linear actuators associated with the audio sensor units based on the relative position of the operator and the audio sensor unit.

[0014] In some exemplary embodiments, detecting the at least one audio signal comprises detecting a plurality of audio signals from a plurality of audio sensor units during assembly of the connector, wherein the plurality of audio sensor units are spaced apart from one another at various locations within the assembly line region; and combining the plurality of audio signals to generate a final audio signal, wherein the testing verifies the assembly of the connector based on the final audio signal.

[0015] In some example embodiments, checking the assembly of the connector includes determining at least one region of interest in the at least one audio signal, deriving features from the at least one audio signal, and predicting whether the connector is correctly or incorrectly assembled based on the derived features and training data.

[0016] In some example embodiments, deriving the features comprises converting the at least one audio signal into an image, wherein the image visually represents the at least one region of interest in the at least one audio signal.

[0017] In some example embodiments, predicting includes determining whether a connector-counterpart signature is found in the derived features by classifying the derived features based on the training data using artificial intelligence.

[0018] In some example embodiments, the method further includes teaching a learning model based on features derived from a training dataset including signatures of properly assembled connectors and signatures of background noise.

[0019] In some exemplary embodiments, the method further includes outputting a verification signal indicating whether the connector is correctly or incorrectly assembled.

[0020] In some example embodiments, the method further includes providing feedback to an operator based on the verification signal.

[0021] In some example embodiments, providing the feedback includes controlling an output device to output a first result in response to the verification signal indicating that the connector is correctly assembled; and controlling the output device to output a second result that is different from the first result in response to the verification signal indicating that the connector is incorrectly assembled.

[0022] In some exemplary embodiments, the method further comprises controlling a cooperating robot to automatically perform assembly of the connector based on data acquired from a guidance sensor; and controlling the cooperating robot to reassemble the connector in response to the check indicating that the connector is incorrectly assembled.

[0023] Further areas of applicability of the present disclosure will become apparent from the detailed description, claims, and drawings. The detailed description and specific examples are for illustrative purposes only and are not intended to limit the scope of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The present disclosure will be more fully understood from the detailed description and the accompanying drawings, in which: Fig. 1 shows a battery assembly for a battery electric vehicle (BEV) according to some embodiments; Fig. 2 shows a close-up view of a latched connector in a battery of a battery electric vehicle (BEV) according to some example embodiments; Fig. 3 shows a system for checking the assembly of a connector according to a first exemplary embodiment; Fig. 4 shows a hardware configuration of a controller of the system for checking the assembly of a connector according to some example embodiments; Fig. 5 shows a software configuration of the controller of the system for verifying the assembly of a connector according to some example embodiments; Fig. 6 shows a method for testing the assembly of a connector according to some example embodiments; Fig. 7 shows a method for detecting the position of an operator according to some example embodiments; Fig. 8 shows a test module according to some exemplary embodiments; Fig. 9 shows a method for performing a test operation according to some example embodiments; Fig. 10 shows a system for testing the assembly of a connector according to a second exemplary embodiment; and Fig. 11 shows a system for testing the assembly of a connector according to a third exemplary embodiment.

[0025] Reference symbols may be reused in the drawings to identify similar and / or identical elements. DETAILED DESCRIPTION

[0026] Example embodiments disclose a system and method for electronically verifying the engagement of a connector during assembly. The verification can be performed in real time, allowing the operator to receive immediate feedback to correct any connector engagement errors before battery pack assembly is complete.

[0027] Fig. 1 shows a battery assembly for a battery electric vehicle (BEV) according to some embodiments, and Fig. 2 is a close-up view of a latched connector in a battery of a battery electric vehicle (BEV) according to some example embodiments.

[0028] With reference to Fig. 1 and Fig. 2, current and future electric vehicle subsystems may increasingly rely on thermal regulation (e.g., heating and / or cooling) to achieve the required performance levels. Properly designed and installed thermal management systems can be critical in this regard.

[0029] A vehicle may include one or more hoses 30 (or alternatively, fluid lines) that circulate a fluid for heating and / or cooling, with each of the hoses formed from a plurality of interconnected segments. The fluid may, for example, be a 50 / 50 mixture of water and antifreeze, such as ethylene glycol. However, the exemplary embodiments are not limited thereto. The segments of the individual hoses 30 may be formed by connecting the segments via connectors 10-1 through 10-n. The connectors 10-1 through 10-n may be plug-in connectors. Plug-in connectors are a popular solution for assembling these hoses 30 during installation in the vehicle and can help enable both efficient and secure connections.The more hoses 30 a vehicle has, the more connectors 10-1 to 10-n are required to ensure safe and effective operation of the vehicle.

[0030] The connectors 10-1 to 10-n are typically installed manually during vehicle assembly by the operator applying manual pressure. However, as subsystems, such as a battery 20, become larger to increase the energy storage capacity and range of the vehicle, it may become more difficult to ensure the correct installation of the connectors 10-1 to 10-n, as the number of connectors 10-1 to 10-n increases and an operator has less space to manually process these connectors 10-1 to 10-n.Furthermore, in hybrid vehicles, electric drive components must coexist with an internal combustion engine and its associated components—including fuel lines, filters, and fuel tank—which can further increase component complexity and density. In these complex environments, it can be particularly difficult to establish and verify the correct connection of the various connectors 10-1 to 10-n. However, reliable connections are critical, as any leak resulting from incorrect assembly can pose a significant safety risk. For example, incorrectly installed connectors 10-1 to 10-n can be difficult to repair after battery 20 is assembled, and incorrectly installed connectors 10-1 to 10-n can lead to fluid leakage from hose 30, which can cause an electrical fire within battery 20.

[0031] While Fig. 1 shows a specific number of hoses 30 connected by a number of connectors 10-1 to 10-n, the number of hoses 30 and connectors 10-1 to 10-n is illustrative and not limiting. The arrangement of the hoses 30 and connectors 10-1 to 10-n relative to the battery 30, as well as the illustrated design of the connectors 10-1 to 10-n, are also illustrative and not limiting.

[0032] Fig. 3 shows a system for checking the assembly of a connector according to a first exemplary embodiment.

[0033] With reference to Fig. 3, a system for checking the assembly of a connector may include a position detection sensor 110, a track 120, at least one actuator 130, an audio sensor unit 140, an automated guided vehicle (AGV) 150, a tracking marker 160, a feedback device 170, and a controller 1000.

[0034] The position detection sensor 110 may be configured to detect the position of an operator and output position data indicative of the operator's position. For example, the position detection sensor 110 may be mounted over an area in the assembly station configured to receive the automated guided vehicle 150, and may be configured to detect the operator's position based on data collected within the area. In some example embodiments, the position detection sensor 110 is a LiDAR (Light Detection and Ranging) sensor configured to detect the operator using a laser. For example, the LiDAR sensor may be used to identify the operator as a moving obstacle within the assembly station based on the laser scan data collected by the position detection sensor 110.In other exemplary embodiments, the position detection sensor 110 may be a camera configured to capture an image of the area and detect the position of the operator from the captured image. For example, the position detection sensor 110 may generate image data that can be used to detect the operator using an image processing algorithm, e.g., a deep sort (Simple Online and Real-time Tracking) model.

[0035] The track 120 may be made of metal and extend longitudinally of the assembly station. It may include a rail on which the at least one actuator 130 can move linearly. The at least one actuator 130 may comprise a pair of 2D linear actuators that move longitudinally along the track 120 in an X-axis direction. It also expands or contracts to move up and down along a Z-axis direction. The 2D linear actuators can convert rotary motion into linear motion. The 2D linear actuators may, for example, be implemented as rack and pinion gears.

[0036] The audio sensor unit 140 may be mounted at one end of the at least one actuator 130. The audio sensor unit 140 may include an audio sensor and a long-range amplifier.

[0037] The audio sensor unit may include a microphone in the form of a transducer that converts sound waves into an electrical signal. The microphone may be a directional microphone, where the microphone sensitivity is directed in one direction, or an omnidirectional microphone, where the microphone sensitivity can be 360 ​​degrees. The long-range amplifier may include a parabolic reflector that collects sound waves and directs them toward the transducer to assist in capturing sound waves from a distance, thus enabling the audio sensor unit 140 to be positioned away from the operator.

[0038] The automated guided vehicle (AGV) 150 can be equipped with navigation and control systems that enable the AGV 150 to move and perform tasks without human intervention. The AGV 150 can be used as a conveyor to transport the battery 20 and other vehicle components along an assembly line.

[0039] The tracking marker 160 may be a tracker, for example, attached to the protective helmet worn by the operator. However, the example embodiments are not limited thereto, and the tracking marker 160 may be attached to any location on the operator that can be detected by the position detection sensor 110. In some example embodiments, the tracking marker 160 may be an April Day or a QR code. In other example embodiments, the tracking marker 160 may be omitted, and the position detection sensor 110 may detect the operator's position, for example, using a machine learning algorithm. For example, the position detection sensor 110 may use a deep sort (Simple Online and Real-time Tracking) model to track the operator's movement within the range of the AVG 150.

[0040] The feedback device 170 may be a display device that provides a visual indication to the operator or other personnel associated with the assembly line. For example, the feedback device 170 may emit a green or red light depending on the test signal it receives. In other exemplary embodiments, the feedback device 170 may provide other forms of feedback to the operator or other personnel associated with the assembly line. For example, the feedback device 170 may emit different tones based on the test signal or may emit different vibration patterns to the operator or other personnel associated with the assembly line based on the received test signal.

[0041] The control unit 1000 may control at least part of the system for testing the assembly of a connector. For example, the control unit 1000 may acquire the position data from the position detection sensor 110 and control the at least one actuator 130 based on the position data. As explained in more detail below, the control unit 1000 may collect audio data from the audio sensor unit 140 and perform a testing process based on the collected audio data. The control unit 1000 may control the feedback device 170 based on a result of the testing process. In some example embodiments, the control unit 1000 may not control the AGV 150, so the AGV 150 may be controlled by a separate control unit. In other example embodiments, the control unit 1000 may also control the AGV 150 to move the AGV 150 along the assembly line.

[0042] Fig. 4 shows a hardware configuration of a control unit of the system for checking the assembly of the connector according to exemplary embodiments.

[0043] With reference to Fig. 4, the control unit 1000 may include processing circuitry 1100, such as at least one processor, at least one communication bus 1200, a memory 1300, and at least one network interface (I / F) 1400. In addition, the control unit 1000 may also include at least one input / output device (I / O device) 1500 (e.g., a keyboard, a monitor, a touchscreen, a mouse, a microphone, a camera, a speaker, etc.), but the example embodiments are not limited thereto.

[0044] In at least one example embodiment, processing circuitry 1100 may include processor cores, distributed processors, or networked processors. Processing circuitry 1100 may be configured to control one or more elements of control unit 1000, thereby causing them to perform various operations. Processing circuitry 1100 is configured to execute processes by retrieving program code (e.g., computer-readable instructions) and data from memory 1300 for processing, thereby performing specific control and functional tasks of control unit 1000. Once the specific program instructions are loaded into the at least one processor, processing circuitry 1100 executes the specific program instructions, thereby transforming processing circuitry 1100 into a specific processor.

[0045] In at least one exemplary embodiment, the at least one communication bus 1200 may enable communication and / or data transfer between elements of the controller 1000. The communication bus 1200 may be implemented using a high-speed serial bus, a parallel bus, and / or any other suitable communication technology. According to some exemplary embodiments, the controller 1000 may include a plurality of communication buses (not shown).

[0046] In at least one exemplary embodiment, memory 1300 may be a non-transitory, computer-readable storage medium and may include random access memory (RAM), read-only memory (ROM), and / or a non-volatile mass storage device such as a disk drive or a solid-state drive. Memory 1300 stores program code (i.e., computer-readable instructions) related to verifying the assembly of a connector as described herein, controlling the at least one network interface 140 and / or at least one I / O device 1500, etc.

[0047] Such software elements may be loaded from a non-transitory, computer-readable storage medium independent of memory 1300, by means of a drive mechanism (not shown) connected to controller 1000, or via the at least one network interface 1400 and / or the at least one I / O device 1500, etc.

[0048] Fig. 5 shows a software configuration of the control unit of the system for checking the assembly of the connector according to exemplary embodiments.

[0049] With reference to Fig. 5, the processing circuit 1100 of the control unit 1000 can execute program code (e.g., computer-readable instructions), retrieved, for example, from the memory 1300, which converts the processing circuit 1100 into a special-purpose processor comprising a position detection module 1110, a test module 1120, and a feedback and control module 1130, which together perform a method for testing the assembly of the connector. The operation of the individual modules 1110 to 1130 is described below with reference to Fig. 6 explained.

[0050] Although the above-mentioned functions are described using the above-mentioned modules 1110 to 1130 for clarity of description, this does not imply that the processing circuit 1100 is limited to these functional units. Thus, in one or more example embodiments, the various operations and / or functions of the functional units may be performed by other functional units. Furthermore, the processing circuit 1100 may perform the operations and / or functions of the various functional units without dividing the operations and / or functions of the computer processing units into these various functional units.

[0051] Fig. 6 shows a method for testing the assembly of the connector according to some example embodiments.

[0052] With reference to Fig. 4-6, the controller 1000 may perform position detection in operation S100. For example, the position detection module 1110 may receive position data from the position detection sensor 110 and detect the operator's position based on the received position data.

[0053] Fig. 7 shows a method for detecting the position of an operator according to exemplary embodiments.

[0054] With reference to Fig. 4-7, the position detection module 1110 may determine whether a trigger is detected in operation S110. In some example embodiments, the trigger may occur, for example, when the AGV 150 has stopped at a preset (or alternatively, a desired) position defining the area in the assembly station, or when the presence of an operator is detected within the area of ​​the AGV 150. However, the example embodiments are not limited thereto. If the position detection module 1110 determines that a trigger has not occurred, the position detection module 1110 may wait until it detects a trigger.

[0055] In operation S120, the position detection module 1110 may continuously detect the operator's position after detecting the trigger. For example, the position detection sensor 110 may continuously generate position data indicating the operator's position based on data continuously collected within the range of the AGV 150 and provide the generated position data to the controller 1000 (e.g., the position detection module 1110).

[0056] In operation S130, the position detection module 1110 may determine whether the audio sensor unit 140 is aligned with the operator. For example, the position detection module 1110 may determine a relative difference between the position of the audio sensor unit 140 and the position of the operator and, based on the difference between the two, determine whether the audio sensor unit 140 is aligned with the operator. Once the position detection module 1110 determines that the audio sensor unit 140 is sufficiently aligned with the operator, the position detection module 1110 may no longer move the audio sensor unit. Instead, the position detection module 1110 may return to operation S120 and continuously monitor the operator's position to determine whether the operator has changed their position within the range of the AGV 150.If the position detection module 1110 determines that the operator has changed their position by more than a threshold value, the position detection module 1110 may determine that the audio sensor unit 140 is no longer aligned with the operator and proceed to operation S140.

[0057] A series of positions may be considered sufficiently aligned based on the empirical measurements of audio data where an audio signal acquired within the series of positions has accurately identified a signature of a correctly mounted connector 10-1 to 10-n using the same or a similar type of audio sensor unit 140.

[0058] If the position detection module 1110 determines at operation S140 that the audio sensor unit 140 is not sufficiently aligned with the operator, the position detection module 1110 may calculate the offset (e.g., the X-axis offset and the Z-axis offset) between the position of the audio sensor unit 140 and the position of the operator.

[0059] At operation S150, the position detection module 1110 may instruct the at least one actuator 130 to move toward the audio sensor unit 140 to align the audio sensor unit 140 with the operator. For example, the position detection module 1110 may instruct the at least one actuator 130 to move in the X direction (e.g., horizontally along a length of the range of the AGV 150) or in the Z direction (e.g., vertically across the range of the AGV 150), or in both of these directions. Once the audio sensor unit 140 is sufficiently aligned with the operator, the position detection module 1110 may generate an alignment signal and return to operation S120 and continue detecting the operator's position to determine if the operator has changed their position by more than a threshold value within the range of the AGV 150.

[0060] With further reference to Fig. 6, the controller 1000 may perform a check operation at operation S200. For example, the check module 1120 may receive the alignment signal from the position detection module 1110 indicating that the audio sensor unit 140 is sufficiently aligned with the operator, and may then perform the check operation.

[0061] Fig. 8 shows a test module according to exemplary embodiments, and Fig. 9 shows a method for performing a test procedure according to exemplary embodiments.

[0062] With reference to Fig. 8 and Fig. 9, an audio receiving module 1122 included in the test module 1120 may buffer and / or process the audio signal received from the audio sensor unit 140 at operation S210.

[0063] At operation S220, a feature extraction module 1124 included in the test module 1120 may receive the processed audio signal, identify the region(s) of interest within the received audio signal, and perform feature extraction of the identified region(s) of interest within the audio signal and output the derived features.

[0064] The region(s) of interest may comprise one or more frequency and / or amplitude ranges previously identified through empirical studies as the signature of the sound produced by the connectors 10-1 to 10-n when correctly assembled, and thus the region(s) of interest may be identified by analyzing the energy distribution of the audio signal captured at the time of assembly of the connectors 10-1 to 10-n by the operator.

[0065] The inspection module 1120 may perform feature extraction by inputting the identified region(s) of interest within the acquired audio signal to a series of signal processing layers that derive features that can be used to predict whether the features include a link-counterpart signature. The inspection module 1120 may generate a visual image of the derived features from the region of interest within the acquired audio signal, where the image may include the link-counterpart signature.

[0066] At operation S230, a prediction module 1126 included in the inspection module 1120 may predict whether the connector, for example, one of the connectors 10-1 to 10-n, is correctly mounted based on whether the connector counterpart signature is found within the derived features based on the training data, and may output a test signal based thereon. For example, the prediction module 1126 may analyze the visual image of the derived features to determine whether the image contains a known visual representation of the connector counterpart signature. For example, the prediction module 1126 may use artificial intelligence to perform classification using a convolutional neural network (CNN) pre-trained based on a deep learning model.The prediction module 1126 may use the tracked model to perform classification based on a classification result.

[0067] The training data may be compiled by a training module 1128. For example, the training module 1128 may receive a recorded dataset, train a model based on the recorded dataset, deploy the trained model, test the trained model, and monitor and record the results. The model may be trained using features derived from a dataset consisting of features from multiple classes, including signatures of correctly fitted connectors 10-1 through 10-n and signatures of classes that are not connectors (background noise, voice, or other abnormal sounds).The recorded results may include true positives when the model correctly predicts a correctly fitted connector 10-1 to 10-n, false positives when the model incorrectly predicts a correctly fitted connector 10-1 to 10-n due to other noise, true negatives when the model correctly predicts an incorrectly fitted connector 10-1 to 10-n, and false negatives when the model incorrectly predicts an incorrectly fitted connector 10-1 to 10-n. The training module 1128 may retrain the model based on the recorded results, for example, by adding true positives and false negatives to the connector dataset and false positives and true negatives to the non-connector dataset.

[0068] With further reference to Fig. 6, at operation S300, the controller 1000 may provide feedback or perform other control operations based on the verification signal. For example, the feedback and control module 1130 may receive the verification signal from the position sensing module 1110 and control the feedback device 170 based on the verification signal. For example, if the verification signal indicates that one of the operator-installed connectors 10-1 to 10-n was correctly installed, the feedback and control module 1130 may control the feedback device 170 to provide positive feedback to the operator. Conversely, if the verification signal indicates that one of the operator-installed connectors 10-1 to 10-n was incorrectly installed, the feedback and control module 1130 may control the feedback device 170 to provide negative feedback to the operator. In some example embodiments, the feedback device 170 may illuminate a light in a first color (e.g.,green) as positive feedback and a light in a second color (e.g. red) as negative feedback.

[0069] However, the exemplary embodiments are not limited thereto. In other exemplary embodiments, the feedback device 170 may output a first tone as positive feedback and a second tone as negative feedback. In other exemplary embodiments, the feedback device 170 may provide haptic feedback to the operator, e.g., a vibration sensation. For example, the feedback device 170 may provide the operator with a first vibration pattern as positive feedback and a second vibration pattern as negative feedback. In other exemplary embodiments, the feedback device 170 may output only a single vibration pattern, e.g., when the test signal indicates correct assembly of a connector, and may not provide any feedback if the connector was not assembled correctly. However, the exemplary embodiments are not limited thereto.

[0070] The controller 1000 can perform the position detection process (S100) and the test (S200) in real time and provide the operator with real-time feedback based on the test results in S300. Therefore, the control unit 1000 can provide the operator with the opportunity to immediately correct incorrectly installed connectors 10-1 to 10-n, even before the final assembly of the battery 20. Thus, the control unit 1000 can ensure the correct assembly of the various connectors 10-1 to 10-n before the final assembly of the battery 20, thus avoiding the significant safety risks caused by incorrectly installed connectors, as well as the significant costs associated with causing these after the final assembly of the battery 20.

[0071] Fig. 10 shows a system for testing the assembly of a connector according to a second exemplary embodiment.

[0072] With reference to Fig. 10, a system for testing the assembly of a connector according to another exemplary embodiment may include a fixed beam 210 instead of a track and a plurality of audio sensor units 140-1 to 140-n mounted on the fixed beam 210. Each of the plurality of audio sensor units 140-1 to 140-n may substantially correspond to the audio sensor unit 140.

[0073] Instead of detecting the operator's position and moving the audio sensor unit to align it with the operator, audio signals may be collected from the plurality of audio sensor units 140-1 to 140-n arranged along the fixed beam 210 within the range of the AGV 150. The test module 1120, such as the audio receiving module 1122, may aggregate the audio data from the plurality of audio sensor units 140-1 to 140-n by synchronizing the audio signals from the plurality of audio sensor units 140-1 to 140-n and processing the synchronized signals as a single aggregate audio signal to detect a link-mate signature.When the connector-counterpart signature is detected, the audio receiving module 1122 may calculate, with a time delay, the sound arriving at each of the plurality of audio sensor units 140-1 to 140-n and may use a triangulation method to determine the location of the sound source. For example, the audio receiving module 1122 may apply a time-of-flight and signal triangulation method to determine the location and / or source of the received sound, thereby identifying which of the connectors 10-1 to 10-n is currently being assembled and, therefore, which of the connectors 10-1 to 10-n may not be properly paired.

[0074] Except for the fact that a plurality of stationary audio sensor units 140-1 to 140-n are mounted on the fixed beam 210 and the position detection sensor 110 is omitted, the connector assembly inspection system according to the second exemplary embodiment may be substantially identical to the connector assembly inspection system according to the first exemplary embodiment. Therefore, a repeated description of the common functions will be omitted for the sake of brevity.

[0075] Fig. 11 shows a system for checking the assembly of a connector according to a third exemplary embodiment.

[0076] With reference to Fig.11, a system for inspecting the assembly of a connector according to a third exemplary embodiment may include a cooperating robot 300. The cooperating robot 300 may include a guidance sensor 310 and an audio sensor unit 340 mounted on the end effector of the cooperating robot 300. The guidance sensor 310 may be a 2D camera configured to visually guide the cooperating robot 300. The audio sensor unit 340 may be substantially the same as the audio sensor unit 140, however, the audio sensor unit 340 may not include a long-range amplifier because it may not be necessary to position the audio sensor unit 140 at a certain distance from the cooperating robot 300.

[0077] The cooperating robot 300 can be controlled by the controller 1000 based on data provided, for example, by the feedback and control module 1130, or it can be controlled by a separate controller. The cooperating robot 300 can automatically assemble the connectors 10-1 to 10-n based on the data acquired by the guidance sensor 310.

[0078] Except for the cooperating robot 300 instead of a position detection sensor 110, a track 120, at least one actuator 130, and an audio sensor unit 140, the system for inspecting the assembly of a connector according to the third exemplary embodiment may be substantially identical to the system for inspecting the assembly of a connector according to the first exemplary embodiment.

[0079] For example, the controller 1000 can predict whether the cooperating robot 300 has correctly assembled the connectors 10-1 to 10-n, essentially in the same manner as described above. Therefore, a repeated description of the common functions is omitted for the sake of brevity.

[0080] In some example embodiments, where the controller 1000 (i.e., the inspection module 1120) predicts that the cooperating robot 300 has incorrectly assembled one or more connectors, the feedback and control module 1130 may control the cooperating robot 300 to automatically reassemble all of the incorrectly assembled connectors 10-1 through 10-n.

[0081] Furthermore, in some example embodiments, the controller 1000 (i.e., the feedback and control module 1130) may control the display device 170 in substantially the same manner as the system for verifying the assembly of a connector according to the first example embodiment. The feedback and control module 1130 may, for example, provide visual, audible, and / or haptic feedback to an operator of the cooperating robot 300 or another person along the assembly line. However, the example embodiments are not so limited, and in the example embodiments, the display device 170 may be omitted, and the feedback and control module 1130 may control the cooperating robot 300 to only reassemble any incorrectly assembled connectors.

[0082] As previously mentioned, exemplary embodiments can help ensure the correct assembly of the various connectors 10-1 through 10-n prior to final assembly of the battery 20, thus avoiding leaks and the significant safety risks that can arise from incorrect assembly of the connectors. Furthermore, exemplary embodiments can provide real-time feedback to the operator or other personnel on the assembly line prior to assembly of the battery 20.

[0083] The above description is merely illustrative and is not intended to limit the disclosure, its application, or uses in any way. The broad teachings of the disclosure may be embodied in a variety of forms. Therefore, although this disclosure includes specific examples, the true scope of the disclosure should not be limited thereto, since other changes will become apparent after studying the drawings, the patent specification, and the following claims. It is understood that one or more steps within a method may be performed in different orders (or simultaneously) without changing the principles of the present disclosure.Furthermore, although the embodiments are each described above as having specific features, each or more of these features described with respect to one embodiment of the disclosure may be implemented and / or combined with features of any of the other embodiments, even if this combination is not expressly described. In other words, the described embodiments are not mutually exclusive, and combinations of one or more embodiments remain within the scope of this disclosure.

[0084] Spatial and functional relationships between elements (e.g., between modules, circuit elements, semiconductor layers, etc.) are described using various terms, including "connected," "engaging," "coupled," "adjacent," "beside," "on top of," "over," "below," and "disposed." If a relationship between first and second elements is not explicitly described as "direct" in the above disclosure, that relationship may be a direct relationship, with no other intervening elements between the first and second elements, or an indirect relationship, with one or more intervening elements (either spatial or functional) between the first and second elements.As used herein, the term "A, B and / or C" should be construed as logical (A ORed with B ORed with C) using a non-exclusive logical OR, and not as "at least one of A, at least one of B and at least one of C".

[0085] In the figures, the direction of an arrow, as indicated by the arrowhead, generally illustrates the flow of information (e.g., data or instructions) of interest to the illustration. For example, if element A and element B exchange a lot of information, but the information passed from element A to element B is relevant to the illustration, the arrow may point from element A to element B. This unidirectional arrow does not imply that no other information is passed from element B to element A. Furthermore, for information being sent from element A to element B, element B may send requests for or acknowledgments of receipt of the information to element A.

[0086] For the purposes of this application, which includes the definitions below, the term "module" or the term "controller" may be replaced by the term "circuit." The term "module" may refer to, be part of, or include: an application-specific integrated circuit (ASIC); a digital, analog, or mixed analog / digital discrete circuit; a digital, analog, or mixed analog / digital integrated circuit; a combinational logic circuit; a field-programmable gate array (FPGA); processor circuitry (common, dedicated, or group) executing code; memory circuitry (common, dedicated, or group) storing code executed by the processor circuitry; other suitable hardware components providing the described functionality; or a combination of some or all of the above components, e.g., in a system-on-chip.

[0087] The module may include one or more interface circuits. In some examples, the interface circuits may include wired or wireless interfaces connected to a local area network (LAN), the Internet, a wide area network (WAN), or combinations thereof. The functionality of any given module of the present disclosure may be distributed among multiple modules connected via interface circuits. For example, multiple modules may enable load balancing. In another example, a server module (also referred to as a remote or cloud module) may perform some functions on behalf of a client module.

[0088] The term "code" as used above may include software, firmware, and / or microcode and may refer to programs, routines, functions, classes, data structures, and / or objects. The term "common processor circuitry" includes a single processor circuitry that executes code from multiple modules, in part or in whole. The term "group processor circuitry" includes a processor circuitry that, in combination with additional processor circuitry, executes code from one or more modules, in part or in whole. References to multiple processor circuitry include multiple processor circuitry on discrete chips, multiple processor circuitry on a single chip, multiple cores of a single processor circuitry, multiple threads of a single processor circuitry, or a combination thereof. The term "shared memory circuitry" includes a single memory circuitry that stores code from multiple modules, in part or in whole.The term “group memory circuit” includes a memory circuit that, in combination with additional memories, stores some or all of the code from one or more modules.

[0089] The term "memory circuit" is a subset of the term computer-readable medium. The term "computer-readable medium," as used herein, does not include transient electrical or electromagnetic signals that propagate through a medium (e.g., on a carrier wave); the term "computer-readable medium" can therefore be considered tangible and non-transitory. Non-limiting examples of a non-transitory, tangible, computer-readable medium include non-volatile memory circuits (e.g., a flash memory circuit, an erasable programmable read-only memory circuit, or a mask read-only memory circuit), volatile memory circuits (e.g., a static random access memory circuit or a dynamic random access memory circuit), magnetic storage media (e.g., an analog or digital magnetic tape or a hard disk drive), and optical storage media (e.g.,a CD, a DVD or a Blu-ray Disc).

[0090] The devices and methods described in this application may be implemented partially or entirely by a special-purpose computer created by configuring a general-purpose computer to perform one or more specific functions contained in computer programs. The functional blocks, flowchart components, and other elements described above serve as software specifications that can be translated into computer programs through the routine work of a skilled technician or programmer.

[0091] The computer programs comprise processor-executable instructions stored on at least one non-transitory, tangible, computer-readable medium. The computer programs may also include or be based on stored data. The computer programs may include a basic input / output system (BIOS) that interacts with the hardware of the special-purpose computer, device drivers that interact with specific devices of the special-purpose computer, one or more operating systems, user applications, background services, background applications, etc.

[0092] The computer programs may comprise: (i) descriptive text to be parsed, e.g. B. HTML (Hypertext Markup Language), XML (Extensible Markup Language) or JSON (JavaScript Object Notation), (ii) assembly code, (iii) object code generated from source code by a compiler, (iv) source code for execution by an interpreter, (v) source code for compilation and execution by a just-in-time compiler, etc. By way of example only, source code can be written using the syntax of languages ​​including C, C++, C#, Objective-C, Swift, Haskell, Go, SQL, R, Lisp, Java®, Fortran, Perl, Pascal, Curl, OCaml, Javascript®, HTML5 (Hypertext Markup Language 5th Revision), Ada, ASP (Active Server Pages), PHP (PHP: Hypertext Preprocessor), Scala, Eiffel, Smalltalk, Erlang, Ruby, Flash®, Visual Basic®, Lua, MATLAB, SIMULINK and Python®.

Claims

[1] A method for testing an assembly of a connector (10-1 to 10-n), the method comprising: Capturing at least one audio signal from the area of an assembly line during assembly of the connector (10-1 to 10-n); Detecting a relative position of an operator and an audio sensor unit (140) within the area, wherein the audio sensor unit (140) is configured to detect the at least one audio signal; and Checking the assembly of the connector (10-1 to 10-n) based on the at least one audio signal. [2] The method of claim 1, wherein the testing tests the assembly in real time while a battery (20) for an electric vehicle comprising the connector (10-1 to 10-n) is assembled on the assembly line. [3] The method of claim 1, wherein detecting the relative position comprises: Detecting an operator's position within the area; Determining whether the position of the operator matches a position of the audio sensor unit (140); and Moving the audio sensor unit (140) toward the position of the operator upon detecting that the position of the operator does not match the position of the audio sensor unit (140). [4] The method of claim 3, wherein detecting the position of the operator comprises: the continuous recording of the operator's position. [5] The method of claim 3, wherein determining whether the position of the operator matches the position of the audio sensor unit (140) comprises: Calculating the offset for the linear actuators associated with the audio sensor unit (140) based on the relative position of the operator and the audio sensor unit (140). [6] The method of claim 1, wherein detecting the at least one audio signal comprises: detecting a plurality of audio signals from a plurality of audio sensor units (140) during assembly of the connector (10-1 to 10-n), wherein the plurality of audio sensor units (140) are spaced apart from one another at different locations within the area of the assembly line; and Combining the plurality of audio signals to produce a final audio signal, wherein the testing checks the assembly of the connector (10-1 to 10-n) based on the final audio signal. [7] The method of claim 1, wherein checking the assembly of the connector (10-1 to 10-n) comprises: Determining at least one region of interest in the at least one audio signal; Deriving features from the at least one audio signal; and Predict whether the assembly of the connector (10-1 to 10-n) is a correct or incorrect assembly based on the extracted features and training data. [8] The method of claim 7, wherein deriving the features comprises: Converting the at least one audio signal into an image, wherein the image visually represents the at least one region of interest in the at least one audio signal. [9] The method of claim 7, wherein the prediction comprises: Determine whether a connector-counterpart signature is found in the derived features by classifying the derived features based on the training data using artificial intelligence.

Images