Abstract: A vehicle assembly according to an exemplary aspect of the present disclosure includes, among other things, an enclosure, a high voltage component housed inside the enclosure and a blocking member configured to restrict access to the high voltage component along a path that extends through the enclosure.

Abstract: A system for defect review and classification is disclosed. The system may include a controller, wherein the controller may be configured to receive one or more training images of a specimen. The one or more training images including a plurality of training defects. The controller may be further configured to apply a plurality of difference filters to the one or more training images, and receive a signal indicative of a classification of a difference filter effectiveness metric for at least a portion of the plurality of difference filters. The controller may be further configured to generate a deep learning network classifier based on the received classification and the attributes of the plurality of training defects. The controller may be further configured to extract convolution layer filters of the deep learning network classifier, and generate one or more difference filter recipes based on the extracted convolution layer filters.

Abstract: An apparatus and method, according to an exemplary aspect of the present disclosure includes, among other things, a battery tray configured to support a plurality of battery cells and at least one cross member positioned between adjacent battery cells. The at least one cross member comprises a base portion that is fixed to the battery tray and an elongated body extending outwardly from the base portion. The elongated body extends from a first end at the base portion to a second end that is opposite the first end, and wherein the first end has a first width and the second end has a second width that is less than the first width.

Abstract: To evaluate a semiconductor-fabrication process, a semiconductor wafer is obtained that includes die grouped into modulation sets. Each modulation set is fabricated using distinct process parameters. The wafer is optically inspected to identify defects. A nuisance filter is trained to classify the defects as DOI or nuisance defects. Based on results of the training, a first, preliminary process window for the wafer is determined and die structures having DOI are identified in a first group of modulation sets bordering the first process window. The trained nuisance filter is applied to the identified defects to determine a second, revised process window for the wafer. A third, further revised process window for the wafer is determined based on SEM images of specified care areas in one or more modulation sets within the second, revised process window. A report is generated that specifies the third process window.

Abstract: An exemplary support assembly for a battery array includes a spacer axially separating a first battery cell from a second battery cell, a frame that holds the spacer, and an insert secured to the frame. The insert is compressed against the first battery cell. An exemplary method of supporting a battery cell includes compressing an insert against a corner region of a battery cell. The insert is secured to a frame made of a first material. The insert is made of a second material that is softer than the first material.

Abstract: An exemplary battery assembly includes, among other things, battery cells distributed along an axis and disposed on a base. A bracket extends axially along a side of the battery cells. A plate extends from a first side to an opposing, second side of the battery cells. A retention flange of the plate is held between the bracket and the base. An exemplary method of retaining includes holding battery cells relative to a base using a bracket extending along a side of the array, and positioning a retention flange of a plate between the bracket and the base. A primary portion of the plate is disposed along an axial end of the array.

Abstract: An apparatus and method, according to an exemplary aspect of the present disclosure includes, among other things, a battery tray configured to support a plurality of battery cells and at least one cross member positioned between adjacent battery cells. The at least one cross member comprises a base portion that is fixed to the battery tray and an elongated body extending outwardly from the base portion. The elongated body extends from a first end at the base portion to a second end that is opposite the first end, and wherein the first end has a first width and the second end has a second width that is less than the first width.

Abstract: To evaluate a semiconductor-fabrication process, a semiconductor wafer is obtained that includes die grouped into modulation sets. Each modulation set is fabricated using distinct process parameters. The wafer is optically inspected to identify defects. A nuisance filter is trained to classify the defects as DOI or nuisance defects. Based on results of the training, a first, preliminary process window for the wafer is determined and die structures having DOI are identified in a first group of modulation sets bordering the first process window. The trained nuisance filter is applied to the identified defects to determine a second, revised process window for the wafer. A third, further revised process window for the wafer is determined based on SEM images of specified care areas in one or more modulation sets within the second, revised process window. A report is generated that specifies the third process window.

Abstract: Machine learning approaches provide additional information about semiconductor wafer inspection stability issues that makes it possible to distinguish consequential process variations like process excursions from minor process variations that are within specification. The effect of variable defect of interest (DOI) capture rates in the inspection result and the effect of variable defect count on the wafer can be monitored independently.

Abstract: A system for characterizing a specimen is disclosed. In one embodiment, the system includes a characterization sub-system configured to acquire one or more images a specimen, and a controller communicatively coupled to the characterization sub-system. The controller may be configured to: receive from the characterization sub-system one or more training images of one or more defects of a training specimen; generate one or more augmented images of the one or more defects of the training specimen; generate a machine learning classifier based on the one or more augmented images of the one or more defects of the training specimen; receive from the characterization sub-system one or more target images of one or more target features of a target specimen; and determine one or more defects of the one or more target features with the machine learning classifier.

Abstract: An exemplary method includes, among other things, providing first and second blanks that are nominally identical and that include an array of raised features. The method further includes removing a first combination of individual raised features from the first blank to provide a first battery component with a first flow path, and removing a different, second combination of individual raised features from the second blank to provide a second battery component with a different, second flow path. An exemplary battery assembly includes, among other things, a blank having a plurality of ribs extending from a floor. The blank is configured such that a first combination of the ribs are removable from the blank to provide a first battery component having first flow path, and a different, second combination of the ribs are removable from the blank to provide a second battery component having a different, second flow path.

Abstract: This disclosure details battery assemblies for electrified vehicles. An exemplary battery assembly may employ one or more compression limiters that maintain the integrity and positioning of a plurality of battery arrays housed inside the battery assembly. The compression limiters may include a body and an attachment head near an end of the body. The attachment head is configured to engage a portion of a support structure of a battery array.

Abstract: A battery pack includes a heat dissipating structure, an array frame positioned against the heat dissipating structure, and a battery cell retained by the array frame and arranged so at least one surface of the battery cell is exposed by the array frame and is contiguous with the heat dissipating structure. The heat dissipating structure may be a heat exchanger plate or a thermal interface material (TIM).

Abstract: An exemplary battery assembly according includes, among other things, a tray, and a cover adjacent the tray to provide a flow path therebetween. The battery assembly further includes a tray boss configured to selectively provide a port through the tray to the flow path, a cover boss configured to selectively provide a port through the cover to the flow path, and a protective fin that is spaced from, and extends at least partially about, the tray boss or the cover boss. An exemplary battery coolant port protection method includes, among other things, forming a cover or a tray with both a boss and a protective fin. The method further removing material from the boss to provide a coolant port to a flow path between the cover and the tray.

Abstract: A battery pack assembly includes, among other things, an enclosure assembly that encloses a lower tier battery array and an upper tier battery array, a lower tier heat exchanger, an upper tier heat exchanger, and a coolant channel of the enclosure assembly. The coolant channel is configured to communicate a liquid coolant between the lower and upper heat exchangers. A battery pack fluid communication method includes, among other things, fluidly coupling together a lower and an upper tier heat exchanger by securing an upper tier floor of a battery pack to a tray of the battery pack.

Abstract: Methods and systems for improved detection and classification of defects of interest (DOI) is realized based on values of one or more automatically generated attributes derived from images of a candidate defect. Automatically generated attributes are determined by iteratively training, reducing, and retraining a deep learning model. The deep learning model relates optical images of candidate defects to a known classification of those defects. After model reduction, attributes of the reduced model are identified which strongly relate the optical images of candidate defects to the known classification of the defects. The reduced model is subsequently employed to generate values of the identified attributes associated with images of candidate defects having unknown classification. In another aspect, a statistical classifier is employed to classify defects based on automatically generated attributes and attributes identified manually.

Abstract: A battery pack includes an array frame having a fastener housing, a mounting insert positioned within the fastener housing, and a column bolt extending through the mounting insert. The mounting insert may be secured to a battery pack enclosure structure using one or more fasteners.

Abstract: Use of care areas in scanning electron microscopes or other review tools can provide improved sensitivity and throughput. A care area is received at a controller of a scanning electron microscope from, for example, an inspector tool. The inspector tool may be a broad band plasma tool. The care area is applied to a field of view of a scanning electron microscope image to identify at least one area of interest. Defects are detected only within the area of interest using the scanning electron microscope. The care areas can be design-based or some other type of care area. Use of care areas in SEM tools can provide improved sensitivity and throughput.

Abstract: A system for defect review and classification is disclosed. The system may include a controller, wherein the controller may be configured to receive one or more training images of a specimen. The one or more training images including a plurality of training defects. The controller may be further configured to apply a plurality of difference filters to the one or more training images, and receive a signal indicative of a classification of a difference filter effectiveness metric for at least a portion of the plurality of difference filters. The controller may be further configured to generate a deep learning network classifier based on the received classification and the attributes of the plurality of training defects. The controller may be further configured to extract convolution layer filters of the deep learning network classifier, and generate one or more difference filter recipes based on the extracted convolution layer filters.

Abstract: Methods and systems for selecting a mode for inspection of a specimen are provided. One method includes determining how separable defects of interest (DOIs) and nuisances detected on a specimen are in one or more modes of an inspection subsystem. The separability of the modes for the Dais and nuisances is used to select a subset of the modes for inspection of other specimens of the same type. Other characteristics of the performance of the modes may be used in combination with the separability to select the modes. The subset of modes selected based on the separability may also be an initial subset of modes for which additional analysis is performed to determine the final subset of the modes.