{"id":4373,"date":"2025-11-25T08:25:22","date_gmt":"2025-11-25T07:25:22","guid":{"rendered":"https:\/\/ghetool.eu\/?post_type=knowledgebase&#038;p=4373"},"modified":"2025-11-25T08:25:22","modified_gmt":"2025-11-25T07:25:22","slug":"modele-ai-pour-accelerer-les-simulations","status":"publish","type":"knowledgebase","link":"https:\/\/ghetool.eu\/fr_fr\/knowledgebase\/ai-model-to-speed-up-simulations\/","title":{"rendered":"Un mod\u00e8le d'IA pour acc\u00e9l\u00e9rer les simulations"},"content":{"rendered":"<p>AI, Artificial Intelligence, is disrupting one industry after another. In this article, we will show you how our new artificial neural network can help you significantly improve the simulation time of GHEtool.<\/p>\n<p><iframe title=\"AI model to speed up simulations\" width=\"800\" height=\"450\" src=\"https:\/\/www.youtube.com\/embed\/9rZNH-UkZ48?feature=oembed\" frameborder=\"0\" allow=\"accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share\" referrerpolicy=\"strict-origin-when-cross-origin\" allowfullscreen><\/iframe><\/p>\n<h2>The overarching problem<\/h2>\n<p>Central to the simulation of borefields is the calculation of g-functions. These non-dimensional functions describe how a borefield behaves in the long-term, with the different boreholes interacting with each other and with the surrounding ground. (If you have not read our article on g-functions, you can find it <a style=\"text-decoration: underline;\" href=\"https:\/\/ghetool.eu\/knowledgebase\/g-functions\/\">here<\/a>.)<\/p>\n<p data-start=\"532\" data-end=\"878\">Historically, the simulation of g-functions, especially for rather large borefields, was extremely slow. Nowadays, due to some clever mathematical tricks and intelligent algorithms, humankind can calculate these g-values in about 0.5 seconds, which is more than acceptable when it comes to the straightforward simulation of borehole temperatures.<\/p>\n<p data-start=\"880\" data-end=\"1312\">However, a problem arises when more complicated and advanced methods require multiple g-values to be simulated, for example in the method calculate required borehole depth. For every iteration, this aim requires the calculation of several g-values, leading to simulation times of ten to thirty seconds or sometimes even higher. With the trend towards more advanced methods, this increase in simulation time is not a bright prospect.<\/p>\n<p data-start=\"1314\" data-end=\"1548\" data-is-last-node=\"\" data-is-only-node=\"\">Therefore, the quest was to find a new way to speed up the simulation of these g-functions without a compromise in accuracy. This is where artificial intelligence, or more precisely an artificial neural network, came into the picture.<\/p>\n<h2>Artificial Neural Network<\/h2>\n<article class=\"text-token-text-primary w-full focus:outline-none [--shadow-height:45px] has-data-writing-block:pointer-events-none has-data-writing-block:-mt-(--shadow-height) has-data-writing-block:pt-(--shadow-height) [&amp;:has([data-writing-block])&gt;*]:pointer-events-auto [content-visibility:auto] supports-[content-visibility:auto]:[contain-intrinsic-size:auto_100lvh] scroll-mt-[calc(var(--header-height)+min(200px,max(70px,20svh)))]\" dir=\"auto\" tabindex=\"-1\" data-turn-id=\"request-WEB:eb633300-ef48-4660-93db-c81ce70d9262-4\" data-testid=\"conversation-turn-10\" data-scroll-anchor=\"true\" data-turn=\"assistant\">\n<div class=\"text-base my-auto mx-auto pb-10 [--thread-content-margin:--spacing(4)] thread-sm:[--thread-content-margin:--spacing(6)] thread-lg:[--thread-content-margin:--spacing(16)] px-(--thread-content-margin)\">\n<div class=\"[--thread-content-max-width:40rem] thread-lg:[--thread-content-max-width:48rem] mx-auto max-w-(--thread-content-max-width) flex-1 group\/turn-messages focus-visible:outline-hidden relative flex w-full min-w-0 flex-col agent-turn\" tabindex=\"-1\">\n<div class=\"flex max-w-full flex-col grow\">\n<div class=\"min-h-8 text-message relative flex w-full flex-col items-end gap-2 text-start break-words whitespace-normal [.text-message+&amp;]:mt-1\" dir=\"auto\" data-message-author-role=\"assistant\" data-message-id=\"f880ab57-7a98-471f-9543-d3c49e05ec5b\" data-message-model-slug=\"gpt-5-1\">\n<div class=\"flex w-full flex-col gap-1 empty:hidden first:pt-[1px]\">\n<div class=\"markdown prose dark:prose-invert w-full break-words light markdown-new-styling\">\n<p data-start=\"139\" data-end=\"479\" data-is-last-node=\"\" data-is-only-node=\"\">AI is a very broad term, encompassing everything from large language models (like ChatGPT) to humanoid robots and self driving systems. Within this AI field, there is something called an artificial neural network (or ANN for short). In the next sections, we will introduce these ANNs, explain how we trained them and what their accuracy is.<\/p>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/article>\n<figure id=\"attachment_4375\" aria-describedby=\"caption-attachment-4375\" style=\"width: 813px\" class=\"wp-caption aligncenter\"><img fetchpriority=\"high\" decoding=\"async\" class=\"wp-image-4375 size-full\" src=\"https:\/\/ghetool.eu\/wp-content\/uploads\/2025\/11\/ANN.jpg\" alt=\"Artist impression of the working of the human brain. (Source: https:\/\/www.snexplores.org\/article\/explainer-what-is-a-neuron)\" width=\"813\" height=\"456\" srcset=\"https:\/\/ghetool.eu\/wp-content\/uploads\/2025\/11\/ANN.jpg 813w, https:\/\/ghetool.eu\/wp-content\/uploads\/2025\/11\/ANN-300x168.jpg 300w, https:\/\/ghetool.eu\/wp-content\/uploads\/2025\/11\/ANN-768x431.jpg 768w, https:\/\/ghetool.eu\/wp-content\/uploads\/2025\/11\/ANN-18x10.jpg 18w\" sizes=\"(max-width: 813px) 100vw, 813px\" \/><figcaption id=\"caption-attachment-4375\" class=\"wp-caption-text\">Artist impression of the working of the human brain. (Source: https:\/\/www.snexplores.org\/article\/explainer-what-is-a-neuron)<\/figcaption><\/figure>\n<p>&nbsp;<\/p>\n<h3>What is it?<\/h3>\n<article class=\"text-token-text-primary w-full focus:outline-none [--shadow-height:45px] has-data-writing-block:pointer-events-none has-data-writing-block:-mt-(--shadow-height) has-data-writing-block:pt-(--shadow-height) [&amp;:has([data-writing-block])&gt;*]:pointer-events-auto [content-visibility:auto] supports-[content-visibility:auto]:[contain-intrinsic-size:auto_100lvh] scroll-mt-[calc(var(--header-height)+min(200px,max(70px,20svh)))]\" dir=\"auto\" tabindex=\"-1\" data-turn-id=\"request-WEB:eb633300-ef48-4660-93db-c81ce70d9262-5\" data-testid=\"conversation-turn-12\" data-scroll-anchor=\"true\" data-turn=\"assistant\">\n<div class=\"text-base my-auto mx-auto pb-10 [--thread-content-margin:--spacing(4)] thread-sm:[--thread-content-margin:--spacing(6)] thread-lg:[--thread-content-margin:--spacing(16)] px-(--thread-content-margin)\">\n<div class=\"[--thread-content-max-width:40rem] thread-lg:[--thread-content-max-width:48rem] mx-auto max-w-(--thread-content-max-width) flex-1 group\/turn-messages focus-visible:outline-hidden relative flex w-full min-w-0 flex-col agent-turn\" tabindex=\"-1\">\n<div class=\"flex max-w-full flex-col grow\">\n<div class=\"min-h-8 text-message relative flex w-full flex-col items-end gap-2 text-start break-words whitespace-normal [.text-message+&amp;]:mt-1\" dir=\"auto\" data-message-author-role=\"assistant\" data-message-id=\"8c2bd447-3f89-4444-a2ea-7864bb6f53e7\" data-message-model-slug=\"gpt-5-1\">\n<div class=\"flex w-full flex-col gap-1 empty:hidden first:pt-[1px]\">\n<div class=\"markdown prose dark:prose-invert w-full break-words light markdown-new-styling\">\n<p data-start=\"116\" data-end=\"678\" data-is-last-node=\"\" data-is-only-node=\"\">The concept of an ANN is to mimic the behaviour of the human brain, or at least the way we think it works. When we receive some sensory input, whether it is smell, touch or sound, it is sent to the neurons in our brain, where the signal moves from neuron to neuron until we end up with a certain thought, action, sense and so on. This behaviour, where we start from a set of inputs and move through a series of neurons to reach a certain conclusion, is exactly what we try to model with an ANN. In the figure below, a schematic representation of an ANN is given.<\/p>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<div class=\"z-0 flex min-h-[46px] justify-start\"><\/div>\n<div class=\"mt-3 w-full empty:hidden\">\n<div class=\"text-center\"><\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/article>\n<div class=\"pointer-events-none h-px w-px\" aria-hidden=\"true\" data-edge=\"true\"><\/div>\n<figure id=\"attachment_4376\" aria-describedby=\"caption-attachment-4376\" style=\"width: 699px\" class=\"wp-caption aligncenter\"><img decoding=\"async\" class=\"wp-image-4376 size-full\" src=\"https:\/\/ghetool.eu\/wp-content\/uploads\/2025\/11\/ANN.png\" alt=\"Schematic representation of an artificial neural network. (Source: https:\/\/blog.roboflow.com\/what-is-a-neural-network\/)\" width=\"699\" height=\"456\" srcset=\"https:\/\/ghetool.eu\/wp-content\/uploads\/2025\/11\/ANN.png 699w, https:\/\/ghetool.eu\/wp-content\/uploads\/2025\/11\/ANN-300x196.png 300w, https:\/\/ghetool.eu\/wp-content\/uploads\/2025\/11\/ANN-18x12.png 18w\" sizes=\"(max-width: 699px) 100vw, 699px\" \/><figcaption id=\"caption-attachment-4376\" class=\"wp-caption-text\">Schematic representation of an artificial neural network. (Source: https:\/\/blog.roboflow.com\/what-is-a-neural-network\/)<\/figcaption><\/figure>\n<p data-start=\"164\" data-end=\"713\">Although these neural networks can come in all shapes and forms, the structure is more or less the same. Starting from a set of input parameters, which in our case is the borefield data (configuration, depth, ground thermal diffusivity and so on), the data passes to a series of nodes in the first layer. Here, in each node (or neuron), the data is weighted by the value in the neuron and sent to the neurons in the next layer. The same process occurs there, until we reach the output layer, which in our case consists of the corresponding g-values.<\/p>\n<p data-start=\"715\" data-end=\"1086\" data-is-last-node=\"\" data-is-only-node=\"\">Depending on the model architecture of your ANN, the number of hidden layers can differ, as well as the number of neurons in each layer. The main challenge is to find a model that is just complex enough to learn or represent the physics you need, and not too over-complicated, since the more neurons you have in your model, the more extensive your training set has to be.<\/p>\n<h3>Training<\/h3>\n<p data-start=\"169\" data-end=\"745\">Just like a baby that comes into this world and still has to learn almost everything, our neural network cannot do anything correctly straight out of the box. As said before, the concept of a neural network is that data passes through several weighting nodes to be transformed, in the end, into the actual output we need. However, these weighting factors are not general but very case specific and model specific. That is why we have to train it and teach the ANN how it should behave, or more specifically for our situation, what the g-values are for a certain set of inputs.<\/p>\n<blockquote><p><span style=\"color: #3366ff;\"><strong>!Note<\/strong><\/span><br \/>\n<span style=\"color: #3366ff;\">The training and development of the ANN for this domain is based on the work of Tobias Blanke, who also developed the ANN model that is currently implemented in GHEtool.<\/span><\/p><\/blockquote>\n<p data-start=\"929\" data-end=\"1116\">For our training dataset, we started from regular configurations (line, L-shaped and U-shaped, rectangles and dense borefields) and simulated them with parameters in the following ranges:<\/p>\n<ul>\n<li>Borefield size: 30&#215;30 boreholes, so up to 900 boreholes for our rectangle and dens shaped borefields.<\/li>\n<li>Borehole depth: 50-400m<\/li>\n<li>Borehole spacing: 2-10m<\/li>\n<li>Borehole diameters: 100-300mm<\/li>\n<li>Ground thermal diffusivity: 2.5e-7 &#8211; 2.67e-6<\/li>\n<\/ul>\n<p data-start=\"1375\" data-end=\"1483\">Given the permutations of all the above data ranges, we trained our model with over six million data points.<\/p>\n<h3>Accuracy<\/h3>\n<article class=\"text-token-text-primary w-full focus:outline-none [--shadow-height:45px] has-data-writing-block:pointer-events-none has-data-writing-block:-mt-(--shadow-height) has-data-writing-block:pt-(--shadow-height) [&amp;:has([data-writing-block])&gt;*]:pointer-events-auto [content-visibility:auto] supports-[content-visibility:auto]:[contain-intrinsic-size:auto_100lvh] scroll-mt-[calc(var(--header-height)+min(200px,max(70px,20svh)))]\" dir=\"auto\" tabindex=\"-1\" data-turn-id=\"request-WEB:eb633300-ef48-4660-93db-c81ce70d9262-10\" data-testid=\"conversation-turn-22\" data-scroll-anchor=\"true\" data-turn=\"assistant\">\n<div class=\"text-base my-auto mx-auto pb-10 [--thread-content-margin:--spacing(4)] thread-sm:[--thread-content-margin:--spacing(6)] thread-lg:[--thread-content-margin:--spacing(16)] px-(--thread-content-margin)\">\n<div class=\"[--thread-content-max-width:40rem] thread-lg:[--thread-content-max-width:48rem] mx-auto max-w-(--thread-content-max-width) flex-1 group\/turn-messages focus-visible:outline-hidden relative flex w-full min-w-0 flex-col agent-turn\" tabindex=\"-1\">\n<div class=\"flex max-w-full flex-col grow\">\n<div class=\"min-h-8 text-message relative flex w-full flex-col items-end gap-2 text-start break-words whitespace-normal [.text-message+&amp;]:mt-1\" dir=\"auto\" data-message-author-role=\"assistant\" data-message-id=\"93bde774-2a14-4e4e-87cd-a4dd9cd505dd\" data-message-model-slug=\"gpt-5-1\">\n<div class=\"flex w-full flex-col gap-1 empty:hidden first:pt-[1px]\">\n<div class=\"markdown prose dark:prose-invert w-full break-words light markdown-new-styling\">\n<p data-start=\"168\" data-end=\"735\" data-is-last-node=\"\" data-is-only-node=\"\">Although there are quite a lot of different formal measures for assessing the accuracy of ANNs, we like to keep it simple and understandable. Therefore, in the graph below, you can see the required borehole depth for nine different cases, calculated with both the regular model (where the g-values are calculated explicitly) and the ANN model. The cases were selected to cover a wide range of situations, such as being limited by the maximum or minimum average fluid temperature, having different geothermal heat fluxes, or having variable fluid properties and so on.<\/p>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/article>\n<figure id=\"attachment_4377\" aria-describedby=\"caption-attachment-4377\" style=\"width: 2273px\" class=\"wp-caption aligncenter\"><img decoding=\"async\" class=\"wp-image-4377 size-full\" src=\"https:\/\/ghetool.eu\/wp-content\/uploads\/2025\/11\/Required-borehole-depth.png\" alt=\"Required borehole depth for 9 different cases simulated with both the regular model and the ANN.\" width=\"2273\" height=\"1091\" srcset=\"https:\/\/ghetool.eu\/wp-content\/uploads\/2025\/11\/Required-borehole-depth.png 2273w, https:\/\/ghetool.eu\/wp-content\/uploads\/2025\/11\/Required-borehole-depth-300x144.png 300w, https:\/\/ghetool.eu\/wp-content\/uploads\/2025\/11\/Required-borehole-depth-1024x492.png 1024w, https:\/\/ghetool.eu\/wp-content\/uploads\/2025\/11\/Required-borehole-depth-768x369.png 768w, https:\/\/ghetool.eu\/wp-content\/uploads\/2025\/11\/Required-borehole-depth-1536x737.png 1536w, https:\/\/ghetool.eu\/wp-content\/uploads\/2025\/11\/Required-borehole-depth-2048x983.png 2048w, https:\/\/ghetool.eu\/wp-content\/uploads\/2025\/11\/Required-borehole-depth-18x9.png 18w\" sizes=\"(max-width: 2273px) 100vw, 2273px\" \/><figcaption id=\"caption-attachment-4377\" class=\"wp-caption-text\">Required borehole depth for 9 different cases simulated with both the regular model and the ANN.<\/figcaption><\/figure>\n<p>It is clear from the graph above that there is excellent agreement between the regular model and the new artificial one. For most cases, the ANN gave a slight overestimation of the required borehole depth, whereas in case 7 a slightly lower depth was simulated. Overall, the accuracy of the ANN was within 4% of the regular model, which is arguably in the order of the other uncertainties used in geothermal design.<\/p>\n<blockquote><p><span style=\"color: #3366ff;\"><strong>!Note<\/strong><\/span><br \/>\n<span style=\"color: #3366ff;\">For accuracy reasons, after the sizing is completed, the temperature profile you see in GHEtool is calculated with the exact, regular model. This means that the AI acceleration is only used to speed up the iteration to find the required depth, but not to simulate the temperatures at this depth. In this way, you have the benefit of a faster model combined with the highest accuracy for the temperature simulation.<\/span><\/p><\/blockquote>\n<article class=\"text-token-text-primary w-full focus:outline-none [--shadow-height:45px] has-data-writing-block:pointer-events-none has-data-writing-block:-mt-(--shadow-height) has-data-writing-block:pt-(--shadow-height) [&amp;:has([data-writing-block])&gt;*]:pointer-events-auto [content-visibility:auto] supports-[content-visibility:auto]:[contain-intrinsic-size:auto_100lvh] scroll-mt-[calc(var(--header-height)+min(200px,max(70px,20svh)))]\" dir=\"auto\" tabindex=\"-1\" data-turn-id=\"request-WEB:eb633300-ef48-4660-93db-c81ce70d9262-11\" data-testid=\"conversation-turn-24\" data-scroll-anchor=\"true\" data-turn=\"assistant\">\n<div class=\"text-base my-auto mx-auto pb-10 [--thread-content-margin:--spacing(4)] thread-sm:[--thread-content-margin:--spacing(6)] thread-lg:[--thread-content-margin:--spacing(16)] px-(--thread-content-margin)\">\n<div class=\"[--thread-content-max-width:40rem] thread-lg:[--thread-content-max-width:48rem] mx-auto max-w-(--thread-content-max-width) flex-1 group\/turn-messages focus-visible:outline-hidden relative flex w-full min-w-0 flex-col agent-turn\" tabindex=\"-1\">\n<div class=\"flex max-w-full flex-col grow\">\n<div class=\"min-h-8 text-message relative flex w-full flex-col items-end gap-2 text-start break-words whitespace-normal [.text-message+&amp;]:mt-1\" dir=\"auto\" data-message-author-role=\"assistant\" data-message-id=\"9b71b445-c2f7-43fc-a610-5c4b796c89d4\" data-message-model-slug=\"gpt-5-1\">\n<div class=\"flex w-full flex-col gap-1 empty:hidden first:pt-[1px]\">\n<div class=\"markdown prose dark:prose-invert w-full break-words light markdown-new-styling\">\n<p data-start=\"1018\" data-end=\"1091\" data-is-last-node=\"\" data-is-only-node=\"\">In the graph below, the simulation time for the different cases is shown.<\/p>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/article>\n<figure id=\"attachment_4378\" aria-describedby=\"caption-attachment-4378\" style=\"width: 2273px\" class=\"wp-caption aligncenter\"><img loading=\"lazy\" decoding=\"async\" class=\"wp-image-4378 size-full\" src=\"https:\/\/ghetool.eu\/wp-content\/uploads\/2025\/11\/Simulation-time.png\" alt=\"Simulation time for the calculation of the required borehole depth for 9 different cases.\" width=\"2273\" height=\"1092\" srcset=\"https:\/\/ghetool.eu\/wp-content\/uploads\/2025\/11\/Simulation-time.png 2273w, https:\/\/ghetool.eu\/wp-content\/uploads\/2025\/11\/Simulation-time-300x144.png 300w, https:\/\/ghetool.eu\/wp-content\/uploads\/2025\/11\/Simulation-time-1024x492.png 1024w, https:\/\/ghetool.eu\/wp-content\/uploads\/2025\/11\/Simulation-time-768x369.png 768w, https:\/\/ghetool.eu\/wp-content\/uploads\/2025\/11\/Simulation-time-1536x738.png 1536w, https:\/\/ghetool.eu\/wp-content\/uploads\/2025\/11\/Simulation-time-2048x984.png 2048w, https:\/\/ghetool.eu\/wp-content\/uploads\/2025\/11\/Simulation-time-18x9.png 18w\" sizes=\"(max-width: 2273px) 100vw, 2273px\" \/><figcaption id=\"caption-attachment-4378\" class=\"wp-caption-text\">Simulation time for the calculation of the required borehole depth for 9 different cases.<\/figcaption><\/figure>\n<p>n the graph above, it is clear that the ANN outperforms the regular approach significantly, with time savings ranging from 25% up to 75%. Taking into account that the difference in accuracy is only 4%, it is fair to say that this is a good trade-off.<\/p>\n<blockquote><p><span style=\"color: #3366ff;\"><strong>!Note<\/strong><\/span><br \/>\n<span style=\"color: #3366ff;\">Besides the calculation time required for the g-functions, other parts of the code also require some time. With the ANN model, the calculation time of the g-values has been reduced significantly, which makes other aspects, such as the calculation of the effective borehole thermal resistance, more dominant in the overall simulation time.<\/span><\/p><\/blockquote>\n<h2>What is next?<\/h2>\n<p data-start=\"195\" data-end=\"292\">So what is next? Will all GHEtool calculations be based on AI models from now on? Absolutely not.<\/p>\n<p data-start=\"294\" data-end=\"668\">Although we have seen and demonstrated the value of relying on AI to accelerate certain methods, we still prefer the accuracy of the regular, physics-based approach. That is why, from today onwards, the ANN is available in GHEtool when using the &#8216;calculate required depth&#8217; aim, under the &#8216;aim specific settings&#8217;. For other methods, it is, in our opinion, not yet an added value.<\/p>\n<p data-start=\"670\" data-end=\"821\">That being said, the implementation of our first ANN opens the door to a whole new range of possibilities, new methods and more advanced optimisations.<\/p>\n<blockquote><p><span style=\"color: #339966;\"><strong>!Stay tuned<br \/>\n<\/strong><\/span><span style=\"color: #339966;\">Next week, we will introduce our first brand-new aim, made possible by this exact ANN. Stay tuned for that!<\/span><\/p><\/blockquote>\n<h2>Conclusion<\/h2>\n<p data-start=\"965\" data-end=\"1276\">This article has laid the foundation for a whole new range of possibilities within GHEtool. With the implementation of an artificial neural network to speed up the simulation time of g-functions, the calculate required borehole depth function can be made 25\u201375% faster while maintaining similar accuracy.<\/p>\n<h2 id=\"reference\">References<\/h2>\n<ul>\n<li>Watch our video explanation over on our YouTube page by clicking <span style=\"text-decoration: underline;\"><a href=\"https:\/\/youtu.be\/9rZNH-UkZ48\" target=\"_blank\" rel=\"noopener\">here<\/a><\/span>.<\/li>\n<li>Blanke, T., Pfeiffer, F., G\u00f6ttsche, J., &amp; D\u00f6ring, B. (2024, September). Artificial neural networks use for the design of geothermal probe fields. In\u00a0<i>BauSim Conference 2024<\/i>\u00a0(Vol. 10, pp. 89-95). IBPSA-Germany and Austria.<\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"<p>L'IA, l'intelligence artificielle, bouleverse les secteurs les uns apr\u00e8s les autres. Dans cet article, nous vous montrerons comment notre nouveau r\u00e9seau neuronal artificiel peut vous aider \u00e0 am\u00e9liorer consid\u00e9rablement le temps de simulation de GHEtool.<\/p>","protected":false},"template":"","pdf-article":[108],"authors":[39],"knowledgebase-category":[26,30],"class_list":["post-4373","knowledgebase","type-knowledgebase","status-publish","hentry","pdf-article-ann","authors-wouter-peere","knowledgebase-category-general","knowledgebase-category-tutorial"],"_links":{"self":[{"href":"https:\/\/ghetool.eu\/fr_fr\/wp-json\/wp\/v2\/knowledgebase\/4373","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/ghetool.eu\/fr_fr\/wp-json\/wp\/v2\/knowledgebase"}],"about":[{"href":"https:\/\/ghetool.eu\/fr_fr\/wp-json\/wp\/v2\/types\/knowledgebase"}],"wp:attachment":[{"href":"https:\/\/ghetool.eu\/fr_fr\/wp-json\/wp\/v2\/media?parent=4373"}],"wp:term":[{"taxonomy":"pdf-article","embeddable":true,"href":"https:\/\/ghetool.eu\/fr_fr\/wp-json\/wp\/v2\/pdf-article?post=4373"},{"taxonomy":"authors","embeddable":true,"href":"https:\/\/ghetool.eu\/fr_fr\/wp-json\/wp\/v2\/authors?post=4373"},{"taxonomy":"knowledgebase-category","embeddable":true,"href":"https:\/\/ghetool.eu\/fr_fr\/wp-json\/wp\/v2\/knowledgebase-category?post=4373"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}