Limitations

• AI Inference Server converts the message data type from data bus according to the following table (left side: type from data bus, right side: converted type how the AI Inference Server handles it). When the data type of an input or output is 'Integer' then the following data bus types can be accepted: 'Int', 'Byte', 'DInt', 'Word', 'LInt', 'SInt', 'USInt','UInt', 'UDInt', 'ULInt', 'DWord', 'LWord', 'Char'.

• AI Inference Server supports configuration package execution based on the following table:

• Maximum payload size with 1 sec / message frequency and 200 MB dedicated memory for Orchestrator:

  • With static payload size (as large string), memory fragmentation does not occur

    • by using SIMATIC S7 Connector v1.6.0-4: 6 Mbytes

    • by using IE MQTT Connector v1.5.1: 10 Mbytes

  • With dynamic payload size, memory fragmentation may occur:

    • by using SIMATIC S7 Connector v1.6.0-4: 6 Mbytes

    • by using IE MQTT Connector v1.5.1: 6 Mbytes

• AI Inference Server converts integer values based on :

• When downloading the logs of an Industrial Edge App, the file is stored with the extension ".tar" by default although the content is a zip archive. Rename the file from .tar to .zip in case the archive reader cannot recognize the archive type by file contents.

• The app could crash if a pipeline contains more variables as the supported (due to memory limit). See table of the configuration package execution in Technical information

• In case of any problem (e.g., restarting of AI Inference Server or restarting of Industrial Edge Device) the logging configuration needs to be re-enabled. (Switch off and switch on)

• If the memory limit is reached during the runtime of a pipeline, then the pipeline execution will crash without warning. The AI Inference Server will continue to work, and an error will pop up in the UI of AI Inference Server, and the process will go into Error state, however, no indication of memory limit reach is visible.

• AI Inference Server swallows a row of input with inter signal alignment. Inter signal alignment assumes a continuous stream of input data and might not handle gaps correctly if the gap length significantly exceeds the defined alignment periodicity. The last alignment window might not be forwarded until a signal belonging to the next alignment window is detected. Workaround for the problem: Test your pipeline and finetune the inter-signal alignment time interval as appropriate for your use case. The test must send one additional row at the end to make sure all the preceding input rows are flushed from the buffer and forwarded to the pipeline.

• Parallel importing on multiple internet browser tabs is not supported Workaround for the problem: Use only one browser tab when you import a configuration package.

• It is not possible to downgrade AI Inference Server to an earlier version via Industrial Edge Management Workaround for the problem: Uninstall the existing app from your Industrial Edge Device and install an earlier version. The previously imported / received pipelines and their mapping information will be lost, you need to re-import and re-map them again.

• The app description (displayed on Industrial Edge Management) is not refreshed after an upgrade process due to an Industrial Edge Management issue.

• LogModule can write strings to the log. Any other type causes a fatal error inside the Runtime and the pipeline is killed, like:

def run (data):

.... log.info([1,2,3])

• "503 Service unavailable" message may appear after the app upgrade (via Industrial Edge Management), the upgraded version of app is not working properly. Workaround for the problem: restart the app

• The data of parameter which is received from the data bus may congest together with the data of variable in case the python script processes it too slow. (Reason: the parameters and the variables are read from the same data connector). The internal queue can be fine-tuned, if necessary. Read the user manual.

• Simultaneous pipeline execution may cause app crash in case the used memory of internal Python Runtime reaches the limit.

• Performance drop might happen in case of multiple pipeline execution (more calculation is required from the same CPU)

• In case the inputs come faster than the Python script can handle them, Out of memory issues may happen. Workaround for the problem: Test your AI models before deploying them to production.

• The app does not check how many CPU core exist. It is possible to set a higher number for the parallel step execution than the available CPU cores. It may cause performance degradation. Maximum 8 cores are supported.

• Data transfer may delay between pipeline steps in case hostname of the ZMQ connection is invalid, and "Object" type is defined for pipeline output. Workaround for the problem: Make sure the outbound ZMQ connection hostname is correct, present, and ready to accept incoming connections.

• There are page rendering problems on Mozilla Firefox browser: the selected tab is not underlined on "Pipeline visualization", "Settings" and "About & legal information" pages.

• Databus app can crash in case of high frequency pipeline input (out of scope of AI Inference Server). Reason: in case the first step (usually a pre-processing) is much slower than the frequency of pipeline input. It may happen the inputs are being piled up in the network layer causing an Out Of Memory crash in the Databus app, which is silently restarted and the AI Inference Server reconnects automatically. Notes: Inter Signal Alignment related use cases are not impacted. For them the inputs are immediately handled and this way they cannot pile up. Workaround for the problem: Creation of an additional pipeline step before the first step which simply forwards it's input as output may help. (in this case, pipeline inputs cannot pile up in the network layer). It can help when there are only a few peaks (longer pre-processing time, but it happens occasionally only) because an internal queue/buffer is in charge between the Pipeline steps. Depending on the data loss app level configuration (in config.json) the pipeline will be stopped with an error message or warning log entries will be created.

• If the pipeline has been deleted by the AI Asset Manager (or AI Model Manager) app, then it is not listed with "Removed" status when the 'Show removed pipelines' toggle switch is activated.

• Statistics & Visualization page is updated in every 2 seconds. There may be situations when the number of input data and output data is different from the values displayed on the user interface. Thus the inference statistics and comprehensive statistics may differ from each other.

• Comprehensive statistics shows the shortest and longest time of a measured part, these values can be connected to different inputs (as shortest or longest time), which can result in a different summary if you try to add these values manually.

• During startup, the following error and warning messages may be logged while synchronizing with external services:

  ..... [API] [E] [mTLS] X.509 stream error:...
  ..... [API] [E] [mTLS] Workload not registered (no identity issued)
  ..... [API] [W] [mTLS] X509 stream ended, restarting... Attempt 1

  This behavior is expected, and AI Inference Server will operate properly once the following info log line appears after one or more attempts:

  .... [API] [I] [mTLS] Reloading TLS context for HTTPS server

• On virtual Industrial Edge Devices where IEVD does not support Secure Production Identity Framework For Everyone (SPIFFE), AI Asset Manager v2.5.0 cannot fully manage AI Inference Server v2.7.0 and is limited to collecting device metric data only.

• Open-Source Components Notes

Components Notes of AI Inference Server GPU accelerated:

Restricted / Copyright © 2025 Siemens Aktiengesellschaft – All rights reserved.

Copying or distribution or communication of the contents of this document are not allowed unless with express written permission from Siemens.