Mirror/AI-on-the-edge-device-docs
1
0
Fork 0
mirror of https://github.com/jomjol/AI-on-the-edge-device-docs.git synced 2025-12-11 22:17:03 +03:00
Code Issues Packages Projects Releases Wiki Activity

Deployed 7c38213 with MkDocs version: 1.4.2

Browse Source
This commit is contained in:
github-actions[bot]
2023-02-03 19:36:11 +00:00
parent 87dc03453b
commit 5b63831461
41 changed files with 272 additions and 270 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
FAQs/index.html
View File

@@ -104,7 +104,7 @@
</li>
<li class="toctree-l1"><a class="reference internal" href="../Configuration/">Configuration</a>
</li>
<li class="toctree-l1"><a class="reference internal" href="../Watermeter-specific-analog---digital-transition/">Analog/Digital Transition on Watermeters</a>
<li class="toctree-l1"><a class="reference internal" href="../Watermeter-specific-analog---digital-transition/">Analog/Digital Transition on Water Meters</a>
</li>
<li class="toctree-l1"><a class="reference internal" href="../collect-new-images/">Collect images to improve the models</a>
</li>
@@ -152,12 +152,12 @@
<ul>
<li class="toctree-l1"><a class="reference internal" href="../outdated--Integrated-Functions/">Integrated Functions</a>
</li>
<li class="toctree-l1"><a class="reference internal" href="../outdated--Gasmeter-Log-Downloader/">Gasmeter Log-Downloader</a>
<li class="toctree-l1"><a class="reference internal" href="../outdated--Gasmeter-Log-Downloader/">Gas Meter Log Downloader</a>
</li>
<li class="toctree-l1"><a class="reference internal" href="../outdated--Migrate-Old-Config-To-New-Config/">Migration from water-meter „old“ to water-meter “AI-on-the-edge-device”</a>
</li>
</ul>
<p class="caption"><span class="caption-text">Asorted Pages</span></p>
<p class="caption"><span class="caption-text">Assorted Pages</span></p>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../Graphical-Configuration/">Graphical Configuration</a>
</li>
@@ -193,7 +193,7 @@
<ul>
<li>Frequent HTML requests</li>
<li>Wrong configuration, missing configuration files</li>
<li>Unstable hardware - see [[Hardware Compatibility]]</li>
<li>Unstable hardware - see <a href="../Hardware-Compatibility">Hardware Compatibility</a>.</li>
</ul>
<p>There is a dedicated page about this: <a href="../Frequent-Reboots/">Frequent Reboots</a>.</p>
<h3 id="how-accurate-are-the-detections">How accurate are the detections?</h3>
@@ -215,10 +215,12 @@
<h2 id="how-can-i-ensure-invalid-numbers-are-never-reported">How can I ensure invalid numbers are never reported?</h2>
<p>As mentioned above, the AI algorithm is not perfect. Sometimes it may read an incorrect value.</p>
<p>We can tune the software to <em>almost</em> never report an incorrect value. There is a tradeoff though: the software may report <em>stale</em> values - i.e. it will drop incorrect values for a potentially long period of time, resulting in the meter reading being outdated by hours. If never receiving an incorrect value is important to you, consider tolerating this tradeoff.</p>
<p>You can change the following settings to reduce incorrect readings (but potentially increase staleness of data):
* Set a prevalue via the UI, then change <code>PostProcessing</code> configuration option <code>PreValueAgeStartup</code> to a much larger number (e.g. <code>43200</code> = 30 days).
* Change <code>PostProcessing</code> configuration option <code>MaxRateType</code> to be time based instead of absolute. Set <code>MaxRateValue</code> to something realistic (e.g. <code>5</code> gal/min). You can often find the max flow rate your meter supports directly on the cover.
* Reduce <code>AutoTimer</code> configuration option <code>Intervall</code> to the lowest it can be (e.g. <code>3</code> min). The more often you take readings, the less likely for data staleness to occur.</p>
<p>You can change the following settings to reduce incorrect readings (but potentially increase staleness of data):</p>
<ul>
<li>Set a prevalue via the UI, then change <code>PostProcessing</code> configuration option <code>PreValueAgeStartup</code> to a much larger number (e.g. <code>43200</code> = 30 days).</li>
<li>Change <code>PostProcessing</code> configuration option <code>MaxRateType</code> to be time based instead of absolute. Set <code>MaxRateValue</code> to something realistic (e.g. <code>5</code> gal/min). You can often find the max flow rate your meter supports directly on the cover.</li>
<li>Reduce <code>AutoTimer</code> configuration option <code>Interval</code> to the lowest it can be (e.g. <code>3</code> min). The more often you take readings, the less likely for data staleness to occur.</li>
</ul>
<h2 id="even-after-i-have-setup-everything-perfect-there-is-a-false-reading-especially-around-the-zero-crossing-roll-over-to-next-number">Even after I have setup everything perfect there is a false reading - especially around the zero crossing (roll over to next number)</h2>
<ul>
<li>The roll over behavior is different for the different meters. E.g.:</li>
@@ -230,7 +232,7 @@
<p>The "PostProcessingAlgo" is trying to judge out of the individual readings, what number it should be. </p>
</li>
<li>
<p>For example if the previous number is a "1", but the next number seems to be a "8.9", mos probably there was a "zero crossing" and the number is a "9" and not still an "8"</p>
<p>For example if the previous number is a "1", but the next number seems to be a "8.9", most probably there was a "zero crossing" and the number is a "9" and not still an "8"</p>
</li>
<li>
<p>Currently the setting of the algorithm is set to fit most of the meters and cases. But the parameters do not fit perfectly for all situations. Therefore there might be intermediate states, where the reading is false.