dns On‑premises cloud Private cloud
Web-native low-code platform for automation of engineering processes at scale:
Brochure picture_as_pdf Documentation Deployment Licensing Get demo access
pSeven Enterprise allowed to automate the simulation processes inside different departments and after that link the dependencies between those simulations in one master workflow to create a full-scale digital prototype of a jet engine.
Repetitive manual operations during compressor map cunstruction such as building geometry models, mesh generation, post-processing of the results and data exchange between different software were automated in pSeven Enterprise.
pSeven Enterprise allows to capture even the most complex engineering processes, define its logic and collect, analyze and reuse engineering data thanks to powerful workflow engine and low-code approach.
pSeven Enterprise is a multi-user platform with simultaneous access and co-authoring of the workflows in the browser. Shared workspaces are designed for departments or teams to share and edit workflows, results and files depending on the user roles - all in your browser in real-time.
pSeven Enterprise runs in a predefined and well-controlled IT environment on-premises or in a private cloud, and can be accessed from any browser or device. As a server-side web application, it allows running many resource-consuming studies simultaneously with a built-in resource manager, and running workflows offline without interruption. You can monitor, manage running process and analyze results anytime from anywhere. Execution of individual blocks is possible both on the Linux server and on remote Windows machines.
Workflows in pSeven Enterprise can be easily published and shared in a form of web apps with either automatically generated or custom developed GUI. These workflow-powered web apps serve as easy-to-use engineering calculators that hide unnecessary complexity and democratize the use of best practices for inexperienced users.
As a collaborative engineering platform, pSeven Enterprise is designed for automating complex simulation workflows and executing them server-side. All workflows are executed server-side in various predefined runtime environments with scalable resource management. All of that makes pSeven Enterprise a reliable backbone for PLM / SPDM systems in terms of handling simulation workflows.
pSeven Enterprise is equipped with a set of tools to efficiently explore model behavior using a wide range of Design of Experiments (DoE) techniques, solve multi-objective optimization problems and perform Uncertainty Quantification (UQ) studies with both fast-to-evaluate analytical models and computationally-expensive simulations.
By creating predictive models*, existing test, experimental, and/or simulation data can be used to predict response values for new designs, accelerate complex simulations by many orders of magnitude and capture essential knowledge.
* - Also often called machine learning models, response surface models (RSM), reduced order models (ROM), approximation models, surrogate models, metamodels etc.
Design Exploration
Explore various design alternatives and easily find optimal solutions with Design of Experiments and Design Optimization strategies.
Uncertainty Quantification
Improve quality and reliability of designed products and manage potential risks at early design, manufacturing and operating stages.
Predictive Modeling
Predict response values for new designs, accelerate complex simulations and capture knowledge by creating fast models from data.
Automatic choosing of algorithms in all tools thanks to SmartSelection technology
When executing a workflow in pSeven Enterprise, each block should ideally run immediately once its input data becomes available - meaning all prerequisite blocks linked to it have completed and produced their outputs. However, block startup often involves initialization delays due to resource allocation for containers, network latencies and other overhead.
pSeven Enterprise offers multiple block execution strategies, each designed to optimize workflow runtime and cluster resource consumption differently. Let's explore how these strategies work using a simple workflow with three sequential blocks.
1. All-at-once: All blocks start simultaneously with the workflow run. Most blocks become ready to process input data by the time it's available, which minimizes inter-block delays. Total workflow runtime then approaches the sum of individual block execution times. Conversely, this leads to excessive cluster load as all blocks reserve required resources upfront.
2. On-demand: Blocks start only when their input data becomes available. Due to initialization delays, blocks cannot immediately start processing input data during the workflow run, which can significantly increase inter-block delays and total workflow runtime. However, this approach minimizes the load by allocating resources only when needed and is recommended for overloaded clusters.
3. On-demand with predictive initialization: The new optimized scheduling strategy (now enabled by default) builds on the on-demand strategy. Using workflow run statistics, it predicts and compensates for block initialization delays. Given accurate timing estimates from previous runs, this strategy ensures each block is ready to execute precisely when its input data (outputs from all prerequisite blocks) becomes available. The updated run strategy maintains low computational overhead comparable to the original on-demand strategy, while achieving runtimes that nearly match the all-at-once strategy. Performance improvements are most significant in workflows with long chains of sequential blocks, while a little less noticeable in highly parallel workflows.
The Model builder block enables predictive modeling in pSeven Enterprise. Data collected from simulations and physical tests can be transformed into an executable model that quickly computes results for any new inputs, accelerating complex simulations by orders of magnitude. For example, such models can be used to run full-factorial experiments and select candidate optimal design parameters, which are then verified using more precise methods.
The process of creating a model is called training, while using a model to compute results for new inputs is called prediction. The overall approach is known as predictive modeling, also referred to as metamodeling, surrogate modeling, response surface modeling (RSM), reduced-order modeling (ROM), machine learning (ML), etc.
Creating a model with sufficiently accurate predictions (good predictive power) requires selecting the most suitable modeling technique for the specific problem and dataset, plus extensive parameter tuning - often through trial and error. In pSeven products, a special technique called SmartSelection automates this entire process without requiring additional configuration or expertise from the user. It automatically searches for an optimal technique and parameter settings to balance computational efficiency and model accuracy based on the training data characteristics.
The Model builder block primarily serves as a SmartSelection launcher within pSeven Enterprise:
Model builder offers quick setup through direct access to all settings in the Block properties pane, requiring no separate UI configuration. The block also features seamless integration with the Design space exploration block, allowing generated DoE to pass directly from the Result designs output to the Training sample input. This integration enables automatic detection of inputs/outputs, names, and properties without requiring additional setup.
For more experienced users, Model builder provides access to the most granular training settings through pSeven Core options. This enables full control over technique selection and parameter configuration. Experts can use Model builder for conventional training workflows while maintaining complete control over the process.
Go to page navigate_nextEngineering simulations often require big files as inputs and in many cases they are needed only as a reference – therefore, there is no need to create a copy of these files in each run.
In recent pSeven Enterprise version we introduced an explicit control over input file handling – users now can decide, which files should be automatically transferred to every Run folder and which they would like to keep at the level of the workflow and access from Runs directly (typically as read-only source of data).
Such control option is also useful when users want to deal with huge files directly on Windows extension node and the transfer is handled by the corresponding integration block – therefore, there is no need for an additional intermediate copy to the Run folder.
Another option to control files access is related to the collaborative nature of the platform. Imagine you published a web app for a wide audience – however, you don’t want the end users to be able to access the internal files of underlying workflow – only the allowed list of result files.
pSeven Enterprise now provides flexible control over such file's exposure, based on an explicit control list - “App result rules”. With this option, authors of the web apps can directly specify which files or folders they want to include or exclude to or from public results.
The eBook highlights the challenges industrial companies of all sizes face in deploying simulation across domains and how pSeven Enterprise addresses those challenges.