Intellect-Partners

Tag: machinelearning

Categories
Semiconductors

Different Semiconductor Packaging Technology

Blog Cover - Semiconductor

Semiconductor packaging

Semiconductor packaging is a crucial component of modern electronics fabrication since it protects and connects integrated circuits to the outside world. IC packaging has developed to satisfy the demands of many applications as electronic devices have grown smaller, quicker, and more adaptable. This article discusses the various kinds of semiconductor packaging, and their significance, used for manufacturing in the semiconductor industry.

Types of Semiconductor Packaging

Semiconductor packaging entails enclosing the semiconductor die within a protective package may be made of ceramic or plastic and connecting the device electrically. The packaging type chosen is determined by criteria such as form factor, thermal concerns, electrical performance, and cost. Here are some examples of several different types of IC packaging:

different types of IC packaging
  • Dual In-line Package (DIP): DIP is one of the oldest semiconductor packaging types, and it remains popular in the industry. It is inserted through the hole-type package in the circuit board. Its pin counts range from 8 to 64.
  • Quad Flat Package (QFP): QFP is a surface-mount package that is rectangular in shape and has leads protruding from all four sides. QFP packages are offered in pin counts ranging from 32 to 304.
  • Small Outline J-lead Package (SOJ): SOJ is a surface-mount package that features J-shaped leads on both sides. SOJ packages are available with pin counts ranging from 8 to 44.
  • Pin Grid Array (PGA): PGA is a through-hole package with pins positioned on the bottom of the package in a grid arrangement. PGA packages come in a variety of pin counts, ranging from 84 to 1,520.
  • Ball Grid Array (BGA): BGA is surface-mount type packaging in which pins in the earlier packaging are replaced with a variety of solder balls. BGA packets come in a variety of ball counts, ranging from 4 to 2,500.
  • Wafer-Level Packaging (WLP): WLP is a packaging method that involves encapsulating the ICs at the wafer level before being divided into individual chips. WLP packages come in a variety of sizes, ranging from 1 mm to 10 mm. Examples include RDL-based, flip-chip, and TSV-based packages. There are main two types of Wafer-level Chip-Scale Packages (WLCSP) that are Fan-In WLCSP and Fan-out WLCSP. Wherein the word “Fan” refers to the chip’s size.
  • Fan-In WLCSP: The Fan-In WLCSP includes the insulating layer, solder balls right on top of the wafer, and package wiring all contributing to the different benefits of a fan-in WLCSP. It has an interposer that is the same size as the die. The electrical transmission channel is relatively short since the solder balls are connected to the chip directly rather than through a medium like a substrate, which enhances electrical properties.
  • Fan-out WLCSP: Fan-out WLCSP overcomes the drawbacks of fan-in WLCSP while retaining its benefits. Fan-out WLCSP has package-mounted solder balls that can be “fanned out” away from the chip. The interposer’s size is the same as that of the die. It also offers good electrical characteristics like FI-WLCSP.
Importance of IC packaging

Importance of IC packaging:

  1. Electrical Performance: The packaging has an impact on the device’s electrical properties, and well-designed packaging reduces signal deterioration and improves overall performance.
  2. Thermal Control: Modern ICs produce a lot of heat. Heat dissipation is facilitated by efficient packaging designs, which helps avoid overheating and ensures long-term dependability.
  3. Form Factor & Size: As electronics get smaller and more portable, miniature packaging techniques make it possible to make devices that are svelte and tiny.
  4. Protection: Different packaging types protect the IC from various conditions including moisture, dust, and temperature changes. The packaging acts as a shield to protect the semiconductor die from these factors.
  5. Interconnect Density: The number of interconnects that may be accommodated depends on the kind of packaging. Complex interconnections are made possible by high-density packing, such as BGAs and CSPs, which is essential for contemporary electronics.

Techinsights images of Wafer level chip scale-type packaging

Samsung Exynos 9110 Processor

Figure 1 Samsung Exynos 9110 Processor (Source)

Apple A14 Bionic Processor (APL1W01)
Apple A14 Bionic Processor (APL1W01)

Figure 2 Apple A14 Bionic Processor (APL1W01) (Source)

IP Trends in Wafer-Level Chip Scale Packaging in Semiconductor

As the importance of packaging is increasing, there is a rapid growth in the patent filing trends witnessed across the globe. The Highest number of patents granted was in 2020 with 3339 patents and the highest number of patent applications filed was ~4553 in 2022.

IBM is a dominant player in the market with ~9319 patent families. So far, it has 1.5 times more patent families than TSMC, which comes second with 5686 patent families. Samsung is the third-largest patent holder in the domain.

Other key players who have filed for patents in WLCSP technology are Intel, Micron, Globalfoundries, SanDisk, Infineon Technology, SK Hynix and so more.

Key players who have filed for patents in WLCSP technology

(Source: Lens.org)

Legal status of patent applications
Patent Documents over Time with Publiation Date

(Source: Lens.org)

Conclusion

IC packaging is a crucial step in the semiconductor business because it shields semiconductor components from corrosion and physical harm from the outside world. The many distinct varieties of IC packages are based on various circuit designs and requirements for the outside shell. The most popular IC packaging designs are wafer-level packaging, pin grid arrays, dual in-line packages, quad flat packages, compact outline J-lead packages, and chip carriers. The IC package you choose depends on the particular application requirements.

Categories
Computer Science

Artificial Intelligence-Based Software Engineering Metrics Defect Identification

Artificial Intelligence, Software Engineering

Nowadays we see the use of Artificial Intelligence (AI) in every field of study, even in image processing, data analytics, text processing, robotics, industries, software technologies, etc. Day by day increasing the use of AI helps users to perform automated tasks without involving the human physically present. The work can be completed automatically within the specified time as per the requirement. Even in the field of Software Engineering, the use of AI is growing day by day to perform automated tasks without causing errors. AI in software engineering provides automated non-error calculations, in the field of software engineering it provides the automated testing of software, automatic debugging of software, etc. to provide high quality (quality assurance), and efficiency of software applications within the budget.

Software Engineering is the method of developing, testing, and deploying computer software to solve problems and issues in the real world by utilizing software principles and best practices. It provides an organized and professional approach from developing the software to the deployment of the software. In the field of software engineering software metrics play a very important role. The software metrics are used to evaluate the reusability, quality, portability, functionality, and understandability. The AI-based software metrics are error-free and automated, they will used to identify or predict the defects in the software and efficient solutions in the real world scenario without involving humans.

Background

Many researchers describe different software metrics and provide efficient solutions for the software metrics. Some research also describes automated solutions using deep learning techniques to improve the software metrics. Without using Artificial intelligence, some chances degrade the quality of the final software products. It may also include a lack of functionality and require more human interactions due to which it increases the cost of the software. Some researchers describe deep learning-based techniques to solve software metrics problems and provide efficient results. However, the can be a lack in using the dataset and training of the data. Using the correct dataset may cause erroneous training of data and provide the wrong results. The wrong results may cause issues and degrade the quality of the software metrics. Therefore, this blog provides the proposed solution that aims to solve the problem of software metrics using Artificial Intelligence.

Basic Concept

According to the authors, there are several studies considered and provided many definitions. Therefore, before discussing the proposed approach let us discuss some basics about the software metrics as discussed.

As discussed above the software metrics are used to evaluate the reusability, quality, portability, functionality, and understandability of the software to achieve high-quality software. The software, metrics are of two types: the system-level metrics and component-level metrics as described in Figure 1.

Software Metrics Categories

Figure 1: Software Metrics Categories

  1. System Level Metrics: The system level metrics are further divided into three types that is Complexity, Metrics Suite, and System Complexity.
  2. Component level Metrics: The component level metrics are further divided into four types that are Customization, component complexity, reusability, and coupling and cohesion metrics.
  • Complexity Metrics: The complexity metrics are the type of system-level metrics. There are many definitions given by many authors. According to IEEE, complexity is defined as the quality where the component or any system design and implementation is complex to understand and authenticate.
  • Metric Suite: It provides the requirements and functionality of the software that is needed by the users. It ensures to provide users a high quality, satisfactory fault-free software products.
  • System Complexity Metric: It is defined as the component metric having a set of components in the system.
  • Customization: The customization metric identifies whether the component can be customized according to the user’s needs or not.
  • Component Complexity Metrics: The Component Complexity Metrics have component plain complexity (CPC), Component Static Complexity (CSC), and Component Dynamic Complexity (CDC).
  • Component Reusability Metric: This type of metric is the ratio of the sum of interface methods that provides common reuse component features used in a feature.
  • Coupling & Cohesion metrics: It is the degree or power with which software components are related to each other.

Proposed Approach

The proposed approach describes the AI-based method to identify as well as predict the defects in the software metrics. In this proposed approach, first, the real-time software metrics dataset is collected from multiple sources. The software metrics dataset may include the data regarding the identified software metrics with labels. The Figure 2 describes the architecture of the proposed approach and systematic details process of this approach.

Figure 2: Proposed Approach

  1. Obtaining data: This step is very essential and very important step of the approach. Correct data means high performance with minimum defects and results in high-quality software. Therefore, in this step, the labeled dataset of the software metrics will be collected. The dataset will include above 50K software modules and the number of defects predicted in the software module. The predicted defects can be binary values in the form of zero and one.
  2. Data Pre-Processing: After data, collection data pre-processing is an essential step of this proposed approach. After data collection, the data must be cleaned and normalized properly to make the analysis simpler and more efficient. In this step, the data is cleaned by removing empty rows, duplicate values, indexing of data, etc.
  3. Artificial Intelligence Model: After data, cleaning the Artificial Intelligence Model will be applied that analyzes the data such as determining the combinations, and automating the detection procedure without human interaction. AI model can be any algorithm applied such as Linear Regression, Logistic Regression, Naïve Bayes, Support Vector Machine, etc. These algorithms will analyze the data and determine the combinations. In this step, the data can also be converted into some kind of vectors also known as numbers based on the software metrics given in the dataset. The AI model is also known as the machine-learning model.
  4. Training and Testing: After the AI model is applied, the data will be split into train sets and test sets that are different from each other. 75% data is given for the train set and the remaining 25% of the data is given for the test set. Then the model is trained on the train set that will train the model based on the combinations and the test set will be used for our model that does not contain any labels, the machine will identify the faults automatically based on the training of the model.
  5. Results: After applying the AI or ML model on the test set the results are obtained on the test set that will determine how best the model works. The results will be determined in terms of accuracy, the area under the curve, f1-score, confusion matrix, etc. The expected accuracy will achieve 98% by applying logistic regression on the test set.

This blog is inspired and in contributed with Dr. Kiran Narang, Department of Computer Science Engineering, SRM University

REFERENCES

[1]. https://www.techtarget.com/whatis/definition/software-engineering
[2]. https://ieeexplore.ieee.org/document/8443016
[3]. https://en.wikipedia.org/wiki/Software_metric
[4]. https://www.sciencedirect.com/science/article/abs/pii/S0925231219316698
[5]. https://www.mdpi.com/2227-7390/10/17/3120
[6]. https://www.sciencedirect.com/science/article/pii/S0164121222002138
[7]. https://viso.ai/deep-learning/ml-ai-models/

Categories
Computer Science Electronics

Nextech AR Launches New SaaS Software Platform “Toggle3D” For CAD-3D Model Market

3D Model, Nextech, Intellect Partners
3D Model

Nextech AR Solutions Corp, a Metaverse Organization and leading supplier of augmented reality (“AR”) experience innovations and 3D model administrations is to report it has launched its Toggle3D, another artificial intelligence powered SaaS platform that empowers the creation, plan, design, and sending of 3D models at scale.

The Organization sees this major launch as a significant achievement while heading on its way to becoming the dominant 3D model platform and anticipates Toggle3D turning into another high-margin engine of development.

Toggle3D is an independent web application that empowers product designers, 3D artists, marketing professionals, and eCommerce website owners to make, customize and publish high-quality 3D models and experiences with no technical or 3D design information required.

The Organization accepts that Toggle3D is the first platform of its kind, and this break-through edge SaaS product is an expected huge advantage for the assembling and design industry, as it gives a feasible answer for converting large CAD (computer-aided design) documents into lightweight 3D models at reasonable prices and scale.

CAD (computer-aided design) is a component of product engineering. Modern engineers, working for product manufacturers, use CAD software like AutoCAD, and SolidWorks to plan large numbers of products in the modern world.

The Toggle3D platform utilized artificial intelligence so those raw CAD files can be converted into photo-realistic, fully textured 3D models at scale. Toggle3D innovation makes optimized 3D meshes that are suitable for 3D and AR applications.

The utilization of CAD documents is universal across assembling verticals including; aerospace, industrial machinery, automotive, civil and construction, pharmaceutical, healthcare, consumer goods, electronics, and others.

As per some reports, the CAD market, measured by the sum spent on the creation of CAD documents, is 11 billion dollars by 2023, so the Organization sees significant use cases for this.

Toggle3D utilizes Nextech AR’s patent-pending innovation artificial intelligence (enabling the transformation of CAD files into 3D models at scale) as well as the Organization’s ARitize Configurator product.

Creators can undoubtedly change their CAD files into 3D models, or carry their current 3D models into the platform. Inside the platform, creators will be able to direct 3 kinds of projects which are all templatized for a fantastic client experience: 3D product Configurators, Virtual Photography, and Item Demos being rolled out throughout the following couple of weeks.

To rapidly acquire early adopters, Toggle3D will be accessible both through a free trial and a pro-SaaS license. A free license will give clients barely enough functionality to evaluate the platform and experiment with the innovation. By upgrading to a pro plan, clients will be given full access to the whole platform’s features.

This incorporates limitless projects, more materials, bigger document uploads, more storage capacity, and other high-level editing tools. It is a self-serve platform, that contains a broad pre-built library of excellent quality 1000 PBR materials. Toggle3D makes things simple, with a friendly UI that works for the users and makes the whole 3D journey consistent.