Method and system for controlling production of biomass

Abstract

The present invention relates to a method for controlling a process of growing a biomass, wherein the method comprises determining a value for a control parameter of the process, and wherein the process comprises mixing together a substrate and mycelium. The present invention also relates to a corresponding system and computer-program product, and to a use of the method and / or system to control the process of growing a biomass.

Description

[0001] Method and System for Controlling Production of Biomass

[0002] Field

[0003] The present invention relates generally to the field of manufacturing processes. More particularly, it relates to methods and systems for controlling and optimizing the process of growing a biomass comprising mycelium.

[0004] Background

[0005] Growing impact of human-induced climate change has spurred significant activity to mitigate addition of further carbon dioxide and other compounds that negatively affect the climate. A particularly significant source of emissions that may negatively affect the climate may be the construction industry. Emissions attributed to the construction industry may be limited not only to those in the production cycle of materials used for construction but also to theirdisposal after use. Consequently, there has been increased focus on alternative materials that may be used for construction. A particularly advantageous development has been materials based on mycelium. Mycelium may be understood to comprise the mass of branched, tubular filaments (hyphae) of fungi.

[0006] Mycelium production has increased several folds in recent years due to the clean-tech sector, focusing on creating novel carbon storing materials. Products based on mycelium may be produced, for example, by combining fungal mycelium with organic leftovers from other industries such as wood fibres, saw-dust, etc. This approach may align with the principles of a circular economy, aiming to limit material and resource waste and store excess carbon in the products.

[0007] A relevant consideration in manufacturing mycelium-based products may, however, be scaling production to volumes needed to replace, at least in part, conventional materials. Large-scale manufacturing may present different efficiency and quality control challenges than small-scale manufacturing. For example, at small-scale, products may be hand-made and quality control may be conducted manually. However, this approach may no longer be feasible for manufacturing on a larger scale. It is an aspect of the present invention to enable, at least in part, automatic quality control for manufacturing of biomass comprising fungal mycelium.

[0008] Yet another consideration in large-scale production and adoption of mycelium-based materials may be lack of process knowledge for optimal production of such biomaterials. While traditional materials used in the construction industry have been around for several years, if not decades, development of mycelium-based materials is in its nascent stages. In particular, in contrast to traditional materials, production of mycelium-based materials may require growing a biomass to a defined stage and then ensuring that there is no further growth or any visual or structural defects in the material. Therefore, growing mycelium-based materials may impose greater demands on process monitoring and control.

[0009] Further, properties of mycelium-based materials may vary significantly depending on an initial recipe (e.g., choice of substrate (e.g., raw materials) or fungal species) and growing conditions (temperature or moisture levels) or other manufacturing process related techniques. In addition to visual appearance, structural properties, strength, fire resistance and hygroscopic properties may vary significantly depending on the production process. The changes in the physical properties of the material, like density, porosity, or specific surface area, may also be attributed to the fact how long the material is allowed to grow. For example, the temperature and moisture levels during the growth stage may affect the strength of the manufactured piece comprising mycelium. More specifically, the structural integrity of the manufactured piece may be attributed to its growing conditions.

[0010] Various techniques have been developed to address these challenges. While satisfactory in many aspects, these techniques may also have their associated disadvantages. In particular, they may rely on manual solutions to the challenges described above that may be inefficient and prone to error.

[0011] Summary

[0012] In light of the above, it is an aim of the present invention to overcome, or at least alleviate, the shortcomings of the prior art. Embodiments of the present invention may allow, at least substantially, fully automated monitoring and control of the process of growing myceliumbased biomass. The mycelium-based biomass may then be used to manufacture various products, particularly as relevant to the construction industry.

[0013] In the following, systems and methods are described for controlling a process for growing a biomass. The process for growing the biomass may be understood to comprise not only a growth stage, but also a dehydration stage. In particular, as described further below, the dehydration stage may be of particular relevance to ensure that further growth does not occur.

[0014] Biomass, as used herein, may be understood to comprise material produced, at least in part, by the growth of microorganisms, plants, or animals. In particular, the material may be produced by the growth of mycelium.

[0015] In the following, communication between any two components of a system may be understood to comprise exchange of data between the two components. Communication between two components may, however, comprise just 1-way communication between two components, wherein data may be sent from one component to another but not vice versa. The details of whether or not a communication is 1-way are described further below. In the following, storing an association between two data elements is described. Storing an association may be understood to comprise storing, for example, a table such that one data element is matched to the other data element and, if needed, inputting one data element outputs the other data element. More generally, a function may be stored, that takes as input one data element and outputs the other, associated data element. As may be appreciated by the skilled person, various data structures may be used to implement such a function.

[0016] In the following, "species of mycelium" has been used. Species of mycelium may be understood to comprise species of fungus, the mycelium of which is used to grow the biomass.

[0017] In the following, various features of the invention have been described with reference to mold. The description with reference to mold may be considered exemplary, but not limiting, of the features of the present technology, and such features may be understood to apply more generally to any form of contamination including, but not limited to, contamination from bacteria.

[0018] Embodiments of the present invention may be of particular relevance for a process for growing a biomass, wherein the process comprises mixing together a substrate and mycelium.

[0019] The process may comprise selecting the substrate. In other words, a control parameter for the process may comprise a choice of substrate from many different available substrates.

[0020] The substrate may comprise one or more substrate components, and selecting the substrate may comprise selecting any of the one or more substrate components. In other words, a control parameter for the process may comprise a choice of a plurality of substrate components from many different available substrates and, preferably, relative fractions of each of the plurality of substrate components. Fractions may be expressed, for example, as fractions of total weight. For example, the substrate may comprise saw dust, or wood fibres such as left-overs from construction.

[0021] The process may comprise selecting a defined quantity of the substrate such that the mixture comprises a defined fraction of the substrate. In other words, a control parameter for the process may comprise, for the choice of a single substrate or a plurality of substrate components, a total fraction of substrate or substrate components in the mixture of substrate and mycelium. The skilled person understands that as mycelium grows, the relative fraction of mycelium in the mixture grows. However, for example, under identical conditions, a mixture with a higher initial fraction of mycelium may result in overproduction of the mycelium as compared to a mixture with a lower initial fraction.

[0022] The process may comprise selecting a species of mycelium. In other words, a control parameter for the process may comprise a choice of species of mycelium from a plurality of different available species. In particular, one or more species may be used and the control parameter may further comprise a relative fraction of each of the chosen species.

[0023] The process may comprise adding an additive to the mixture.

[0024] The process may comprise adding a plurality of additives to the mixture.

[0025] The process may comprise selecting the additive or any of the plurality of additives to add to the mixture. In other words, a control parameter for the process may comprise a choice of the one or more additives and, preferably, their relative fractions.

[0026] The process may comprise sterilizing the substrate. The substrate may be sterilized prior to adding the fungi and any other components as described above. This may be of advantage in preventing growth of undesired micro-organisms in the biomass.

[0027] The process may further comprise heat-treating, steam / vapor-treating, or UV-treating the substrate. In other words, a control parameter for the process may comprise, for example, a temperature or pressure at which the substrate is sterilized. Alternatively, or additionally, the control parameter may comprise a duration for which the substrate is treated with UV radiation.

[0028] The process may further comprise admixing the substrate with mycelium. In other words, the substrate may be inoculated with mycelium. Inoculation of the substrate may be carried out by seeding with liquid or solid mycelium.

[0029] The process may further comprise storing the mixture in conditions suitable for growth for a plurality of days.

[0030] The plurality of days may comprise less than 7 days, or more than a week, or more than a few weeks, or even a few months. Conditions suitable for growth may comprise, for example, an optimal level of moisture in the mixture, provision of light, or other suitable conditions as further described below.

[0031] The process may comprise a growth stage, wherein the growth stage may comprise a stage of growth of the mycelium.

[0032] The process may comprise a dehydration stage, wherein the dehydration stage may comprise dehydrating the biomass. Dehydrating the biomass may, in particular, stunt the growth of the mycelium such that a desired level of growth of mycelium may be achieved.

[0033] Dehydrating the biomass may comprise evaporative dehydration. Evaporative dehydration may be effected by use of any of a high temperature, a low ambient humidity, and blowing air (or any other suitable gas) over a surface of the biomass. In other words, a control parameter for the process may comprise, for example, a temperature to which the biomass is subjected, a presence / absence and power control of a dehumidifier, or a speed at which air is blown over the surface of the biomass respectively.

[0034] Dehydrating the biomass may comprise irradiating the biomass.

[0035] The process may comprise irradiating the biomass, at least in part, with microwave radiation.

[0036] The process may comprise irradiating the biomass, at least in part, with infrared radiation. In other words, a control parameter for the process may comprise a wavelength of radiation with which the biomass is irradiated and / or an energy of irradiation.

[0037] Dehydrating the biomass may comprise using a furnace or oven.

[0038] Dehydrating the biomass may comprise increasing a temperature of the biomass up to 90°C, preferably up to 100°C, further preferably up to 150°C, yet further preferably up to 230°C.

[0039] Dehydrating the biomass may comprise reducing the temperature of the biomass to room temperature. A relevant consideration may be the rate at which the biomass is dried / dehydrated. A higher than optimal rate of dehydration may lead to formation of cracks, whereas a lower than optimal rate may lead to inefficiency. Therefore, a control parameter of the process may comprise a rate of dehydration of the biomass that may be determined, for example, by determining a moisture level of the biomass over time. Depending on how long the material is grown and its characteristics, it may, for example, be more resilient to higher amplitudes of temperatures and humidity levels, so the drying process may be further optimized.

[0040] The growth stage may be followed by the dehydration stage.

[0041] A result of dehydrating the biomass may be, at the end of the dehydration stage, a moisture level of the biomass being in the range defined by 5% and 50%, preferably by 5% and 40%, further preferably by 5% and 30%.

[0042] A result of the process may be, at the end of the process, a pH level of the biomass being in the range defined by 4.5 and 7.5, preferably by 4.8 and 7.2, further preferably by 5 and 7. The pH may be controlled, for example, by adding water and additives. The control parameter may, then, comprise, for example, an amount of water / additive to be added, a composition of a mixture of water and additives, a duration of the overall bioprocess (e.g., growing time) or other suitable parameters.

[0043] According to a first aspect, the present invention relates to a method for controlling a process of growing a biomass, wherein the method comprises: determining a value for a control parameter of the process. The control parameter may comprise, inter alia, any of the control parameters described above. Further examples of control parameters that may be relevant are described below. Embodiments of the present technology may, in particular, allow controlling the process at least semi-automatically, preferably fully automatically, by determining and setting value(s) for the control parameter(s) of the process.

[0044] The process may comprise a process as described above.

[0045] The method may comprise sending the value for the control parameter to a control unit. The control unit may, in particular, be configured to set the value of the control parameter to the value determined as described above.

[0046] Determining the value for the control parameter may comprise using a model. A model may be understood to accept an input and produce an output based, at least in part, on the input.

[0047] The model may comprise, at least in part, a heuristic model. A heuristic model may be understood to comprise a model that captures known relationships between control parameters of the process and a resulting outcome. For example, if the humidity is increased by 10%, the rate of growth may increase by 1%. A heuristic model may be of advantage in providing more robust and accurate control of the process. However, owing to the complexity of the process, it may be difficult, if not impossible, to obtain a heuristic model for the process.

[0048] The model may comprise, at least in part, an artificial intelligence-based model. An artificial intelligence-based model may be of particular advantage in controlling the process. The artificial intelligence-based model, as described herein, may allow determining value(s) for control parameter(s) such that an optimal growth of biomass may be achieved.

[0049] The artificial intelligence-based model may comprise a trained model.

[0050] The method may comprise receiving the trained model. Receiving the model may be understood to comprise receiving, for example, a set of tensors, each tensor representing a layer in a neural network, together with an order on the set of tensors, wherein the order may define the order of different layers in the neural network. Receiving a tensor may be understood to comprise receiving a set of numbers corresponding to the values of different components of the tensor. Alternatively, the model may comprise a set of numbers, each number representing a threshold for each level of a decision tree or a random forest. Generally, any representation suitable to the model may be used.

[0051] The method may comprise generating the trained model, generating the trained model comprising training a model.

[0052] Generating the trained model may comprise training the model, at least in part, using supervised learning. For example, the value for the control parameter may be already known for reducing formation of cracks in the biomass. The model may then be trained, given a presence of a crack in the biomass, to output the known value, or at least a value close thereto.

[0053] Generating the trained model may comprise training the model, at least in part, using unsupervised learning.

[0054] The method may comprise storing the trained model. Storing the trained model may be understood, for example, to comprise storing values for components of a tensor.

[0055] The method may comprise sending the trained model.

[0056] The method may comprise receiving data from a sensor, that may be referred to as sensor data. The sensor data may comprise the data measured by the sensor. For example, a temperature sensor may be configured to measure a temperature. The sensor data may, then, comprise the temperature.

[0057] The method may further comprise receiving data related, at least in part, to the sensor data. The data related, at least in part, to the sensor data may comprise data associated with the sensor data such as a time at which the data was recorded. Alternatively, or additionally, the data related, at least in part, to the sensor data may comprise the last value for the control parameter. Generally, the data related, at least in part, to the sensor data may allow establishing, at least substantially, a causal relationship between the value for the control parameter and a resulting state of the biomass. The establishment of the, at least substantially, causal relationship may be of particular advantage in allowing the model to be used for control of the process.

[0058] The method may comprise determining the value for the control parameter based, at least in part, on the sensor data, or the data related, at least in part, thereto.

[0059] The method may comprise sending the sensor data, or at least data related thereto, as input to the model.

[0060] The sensor data may be related, at least in part, to a current state of the biomass. A state of the biomass may be understood to comprise all measurable properties of the biomass. For example, the current state of the biomass may be described by means of a weight of the biomass.

[0061] Determining the value for the control parameter may be based, at least in part, on an output of the model. Training the model may comprise sending labeled data as input to the model, the labeled data comprising a label, wherein the label relates, at least in part, to a desired value for the control parameter.

[0062] Training the model may comprise comparing an output of the model to the label.

[0063] Training the model may comprise updating the model based, at least in part, on a result of comparing the output of the model to the label.

[0064] The labeled data may comprise data at least similar to the sensor data. In particular, the data at least similar to the sensor data may comprise data for which a desired value for the control parameter is known. For example, the sensor may comprise a camera and the sensor data may comprise an image of the biomass. The image of the biomass may depict a crack in the biomass. The desired value for the control parameter may then comprise a value that may reduce the formation of cracks in the biomass.

[0065] The method may comprise storing the sensor data. The method may further comprise storing the data related, at least in part, to the sensor data.

[0066] The method may comprise retrieving stored sensor data.

[0067] The stored sensor data may be related, at least in part, to a previous state of the biomass.

[0068] The method may comprise sending the retrieved sensor data, or at least data related thereto, as input to the model. In particular, the artificial intelligence-based model may be trained to use, at least in part, the previous state(s) of the biomass to determine the value for the control parameter. For example, the artificial intelligence-based model may be configured for timeseries analysis wherein a variation over time in the sensor data may be input to the model. The value for the control parameter may be determined based, at least in part, on the input time variation of the sensor data.

[0069] Determining the value for the control parameter may be based, at least in part, on sensor data related, at least in part, to a previous state of the biomass.

[0070] The method may comprise directing a beam of particles at the biomass, or at least a part thereof. The particles may comprise any of photons, electrons, ions, or any other suitable particles. In particular, the method may comprise directing a plurality of beams of particles at the biomass, the plurality of beams of particles comprising particles differing in kind (e.g., electrons and photons), or differing in energy (e.g., high-energy and low-energy electrons), or differing in polarization (e.g., plane-polarized and circularly-polarized photons), or any combination thereof. The sensor may comprise a particle sensor. It may be appreciated that the particle sensor may comprise an appropriate particle sensor according to a particle desired to be sensed. For example, the particle sensor may comprise a photon sensor, an electron sensor, or an ion sensor. In particular, the sensor may comprise a plurality of particle sensors, wherein a first of the plurality of particle sensors may detect a first kind of particles such as electrons, for example, and a second of the plurality of particle sensors may detect a second kind of particles such as photons. Further, any two of the plurality of particle sensors may also detect the same kind of particles but may have different sensitivities to different energies of the particles detected. For example, the plurality of the particle sensors may comprise two photon sensors, one of the two photon sensors with high sensitivity to photons in the optical wavelength, whereas the other with high sensitivity to photons in the infrared wavelength.

[0071] The method may comprise detecting, using the particle sensor, particles transmitted and / or reflected by the biomass.

[0072] The sensor may comprise a camera. A camera may be understood to comprise a particle sensor that also has a non-zero spatial resolution that may allow formation of images based on the sensed particles.

[0073] The particle sensor may comprise a photon sensor, wherein the photon sensor is configured to sense photons with a wavelength in the range defined by 200 nm and 2500 nm, preferably by 300 nm and 2000 nm, further preferably by 400 nm and 1500 nm. Further, the photon sensor may be configured to detect photons with much higher wavelengths such as wavelengths up to 15000 nm. For example, the photon sensor may detect photons in the wavelength range defined by 2000 nm and 15000 nm, preferably by 3000 nm and 14000 nm, further preferably by 8000 nm and 14000 nm. In other words, the camera may comprise an optical camera, a UV-camera, or an IR-camera. In particular, multiple cameras may be used, wherein each camera may be configured for imaging in a different wavelength band.

[0074] The data received from the camera may comprise an image.

[0075] The labeled data may comprise an image.

[0076] The label may be related, at least in part, to a crack, a defect, a deformation, or contamination in the image. In particular, the label may relate only to a presence of a crack, defect, deformation, or contamination in the image, but may also relate to a location and / or extent of the crack, defect, deformation, or contamination. In other words, the labeled data may comprise an image together with a label indicating a crack, defect, deformation, or contamination in the image. Contamination may occur, for example, due to growth of mold, bacteria, or other micro-organisms in the biomass. The skilled person understands that the presence of crack, defect, deformation, or contamination in the image corresponds to the presence of such features in the biomass such that they are then visible also in the image. A crack may be defined as a rip in a surface of the biomass, a deformation as a deviation of the biomass from a defined shape, whereas a defect may relate to aspects of growth of mycelium in the biomass such as an over / under growth, non-spatially-uniform growth, among others.

[0077] Further, while the embodiments described herein refer explicitly to an image, the skilled person understands that aspects of the present technology may apply, generally, to any kind of data that may allow detection (i.e., presence of) and / or characterization (i.e., position, size, etc. of) a crack, a defect, a deformation, or contamination in the biomass. For example, such data may comprise scan data from scanning a surface of the biomass. The scan may, for example, comprise a scanning or atomic force microscope scan or another electromagnetic scanning technique known to the skilled person. In some other embodiments, the scan may also comprise an acoustic scan of the biomass as obtained, for example, by an ultrasound scan, or measuring an acoustic response of the biomass.

[0078] Generally, any kind of data may be used as long as appropriate training data is available therefor. Appropriate training data may be understood to comprise labeled data that may comprise measurement data (that may include an image as described above), as measured from the biomass, and a label as described herein.

[0079] The label may be related, at least in part, to a desired value for the control parameter to, at least, mitigate formation of a crack, a defect, a deformation, or contamination in the biomass.

[0080] The method may comprise detecting, using, at least in part, the model, any of a crack, a defect, a deformation, or contamination in the image. Detecting a crack, a defect, a deformation, or contamination may comprise detecting only the presence of the crack, defect, deformation, or contamination in the image. Alternatively, or additionally, detecting the crack, defect, deformation, or contamination may comprise determining a location in the image of the crack, defect, deformation, or contamination. As may be appreciated, the determination of the location may be more time- and resource-intensive as compared to detection of only the presence. However, determination of the location may provide more information about the growth of the biomass, possibly allowing a localized control of the growing process.

[0081] The method may comprise, in response to having detected any of a crack, a defect, a deformation, or contamination in the image, determining, using, at least in part, the model, a value for the control parameter to, at least, mitigate formation of any of a crack, a defect, a deformation, or contamination in the biomass.

[0082] Thus, in general, the model may comprise, for example, two sub-models, one of the two submodels configured to detect a crack, defect, deformation, or contamination in the biomass, and the other of the two sub-models configured to determine the value for the control parameter based, at least in part, on a result of detection by the first sub-model. The submodel for detection of cracks, defects, deformations, or contamination may be based, for example, on any suitable image processing algorithm available.

[0083] The training of the model may comprise, at least in part, comparing the detected crack, defect, deformation, or contamination in the image and / or the predicted value for the control parameter with the label(s) as described above. In particular, the two sub-models, as described above, may be trained individually or together.

[0084] The determination of the value for the control parameter may be based, for example, on a kind of crack, an extent of the crack, and / or on a comparison of the current state of the biomass to a previous state of the biomass (with a smaller or larger crack, for example). As may be appreciated, the same considerations may also apply to defects, deformations, and contamination. Comparison of the current and previous states of the biomass may allow determining whether or not the previous value for the control parameter had a desired effect, such as reducing a rate of growth of a crack.

[0085] The method may comprise, in response to having detected any of a crack, a defect, a deformation, or contamination in the image, generating a notification. The notification may comprise, for example, an acoustic notification. Alternatively, or additionally, the notification may comprise a visual notification. Yet further alternatively, or additionally, the notification may comprise an API request.

[0086] The method may comprise automatically positioning a source of the particles and / or the particle sensor. Positioning the source of the particles and / or the sensor may be of advantage in obtaining information about different regions of the biomass. Further, the source of particles may comprise a light source that may promote growth of the mycelium, and may be positioned to effect more spatially uniform growth. Thus, the position of the source of particles may also be used as a control parameter for the process.

[0087] The method may comprise using the control unit to position the source of the particles and / or the particle sensor.

[0088] The sensor may comprise a probe.

[0089] The sensor data may be based, at least in part, on a motion of the probe. For example, the probe may comprise a probe of an atomic force microscope that may be used to determine a topography and / or a molecular composition of the biomass. The topography of the biomass may be of advantage in determining, for example, a morphology of the biomass such as a surface roughness of the biomass. The method may comprise directing the probe to establish contact with the biomass, or at least a part thereof.

[0090] The method may comprise automatically directing the probe to establish contact with the biomass, or at least a part thereof.

[0091] Directing the probe may comprise positioning the probe over the biomass, or at least a part thereof.

[0092] The method may comprise using the sensor to determine a moisture level of the biomass, or at least a part thereof. The moisture level may be expressed, for example, as a percentage. However, other expressions may also be possible. Moisture level may, for example, be in the range defined by 30% and 80%.

[0093] Different moisture level sensors may be provided for different stages of the process. In particular, for example, moisture level may be expected to be high in the growth stage, and low in the dehydration stage. Thus, for example, a moisture level sensor for the growth stage may be, advantageously, sensitive to moisture levels above 50%, whereas a moisture level sensor for the dehydration stage may be sensitive to moisture levels below 40%. As may be appreciated, these values are only exemplary and the thresholds may vary depending, for example, on the species of mycelium used.

[0094] The method may comprise using the sensor to determine a temperature of the biomass, or at least a part thereof. Temperature may be estimated, for example, by means of an image of the biomass captured by a thermal camera. In particular, the temperature may indicate, at least in part, a surface temperature of the biomass.

[0095] The method may comprise using the sensor to determine a pH level of the biomass, or at least a part thereof.

[0096] The method may comprise using the sensor to determine a density of the biomass, or at least a part thereof. Density may be measured, for example, by measuring a weight of the biomass and estimating a volume of the biomass based, at least in part, on an image of the biomass. For example, the biomass may be grown and / or dried in a container that may be arranged on a scale. The measurement of the scale may be recorded, for example, periodically. The camera, as described above, may be used to capture an image of the biomass at, at least substantially, the same time as the recording of the weight.

[0097] The method may comprise using the sensor to identify a region of undergrowth or overgrowth in the biomass, or at least a part thereof. The sensor may comprise a humidity sensor, and the method may comprise determining a humidity of an environment in which the biomass is being grown and / or dehydrated. Thus, the sensor may not only determine properties of the biomass, but also of an environment in which the biomass is being grown and / or dehydrated. Control of the process may be effected more easily by controlling the environment of growth and / or dehydration of the biomass.

[0098] The sensor may comprise a temperature sensor, and the method may comprise determining a temperature of an environment in which the biomass is being grown and / or dehydrated.

[0099] The sensor may comprise a concentration sensor, and the method may comprise determining a concentration of a gas in an environment in which the biomass is being grown and / or dehydrated.

[0100] The sensor may comprise a gas sensor. The gas sensor may be configured to determine the presence, availability, or absence of a defined gas.

[0101] The sensor may comprise a liquid-state sensor that may be configured to determine a sugar content and / or a turbidity of a liquid inoculum comprising a suspension of mycelium in a liquid medium, particularly an aqueous medium. In other words, the substrate as described above, may comprise a liquid medium and the mixture of mycelium and the substrate may comprise the liquid inoculum. The liquid-state sensor may be configured to measure properties of this mixture. The measured properties may, as understood by the skilled person, be control parameters that may also be controlled to control properties of the resultant biomass.

[0102] As the skilled person understands, the inoculum may grow in the liquid medium, reproducing the mycelium (fungal biomass) by utilizing nutrients that may be dissolved and available in the liquid medium. The liquid-state sensor may be a gas sensor, that can be submerged into the mixture. The liquid-state sensor may also measure availability of nutrients (i.e. sugar content), pH, and detect / quantify concentration of target chemical compounds (metabolites) or gas, which can be produced in the process.

[0103] The particle sensor may comprise a photon sensor, and the method may comprise determining a brightness in an environment in which the biomass is being grown and / or dehydrated. Brightness may be determined, for example, by measuring an intensity of light incident on the photon sensor. In particular, as described above, the photon sensor may be configured to detect photons in a wide range of wavelengths. The intensity of incident light may be detected in at least some part, preferably all, of this range of wavelengths. Thus, for example, intensity may also be determined in IR wavelengths.

[0104] The biomass may be characterized by a characterization parameter, the characterization parameter having a characterization value. The method may comprise determining the characterization value of the characterization parameter based, at least in part, on the sensor data, or the data related, at least in part, thereto.

[0105] The data related, at least in part, to the sensor data may comprise a timestamp related, at least in part, to a time at which the sensor data, or at least a part thereof, is recorded. For example, the timestamp may correspond to a time at which the sensor data is recorded. However, in some embodiments, the timestamp may, alternatively, correspond to a time at which the sensor data is sent.

[0106] The control unit, as described above, may be configured to control an actuator, and the method may comprise activating and / or deactivating the actuator based, at least in part, on the value for the control parameter.

[0107] The method may comprise storing the determined value for the control parameter.

[0108] The method may comprise storing a time at which the value for the control parameter is sent to the control unit. Storing of the determined value may, thus, allow establishing the, at least substantially, causal relationship between the value for a control parameter and the growth of the biomass. By means of storing the times at which the value(s) for the control parameter(s) are determined / sent, the time at which the sensor data is recorded, the determined value(s) for the control parameter(s), and the recorded sensor data, the model may be able to "learn" the influence of the value(s) over the growth / dehydration process, allowing optimal control of the process.

[0109] The method may comprise providing a desired characterization value for the characterization parameter as input to the model.

[0110] The method may comprise determining the value for the control parameter based, at least in part, on the desired characterization value.

[0111] The label may be related, at least in part, to a desired value for the control parameter to grow biomass characterized by the characterization parameter of value, at least significantly, identical to the labeled data. In other words, the model may be configured to determine the value for the control parameter such that the desired value of the characterization parameter is, at least substantially, reached.

[0112] The characterization parameter may comprise any of a density, a Young's modulus, a hydrophobicity, a water retention capacity, a fire-retardation capacity, or an appearance of the biomass. The characterization value for the appearance may comprise, for example, an image of the biomass. Thus, the model may, for example, accept as input, an image of a desired biomass and the model may output the value for the control parameter such that the desired biomass is, at least substantially, realized. The appearance may further comprise, for example, a color distribution of an image. The color distribution may indicate a stage of growth of the biomass. For example, when the color is dominated by a color of a substrate, the biomass may be in an early stage of growth. Alternatively, as the color becomes dominated by a color of the mycelium, an advanced stage of growth may be indicated. For example, in some embodiments, saw-dust may be used as a substrate, while mycelium may be visible as, at least significantly, a white color. Then, dark / brown / woody spots may indicate substrate (undergrowth), barely white spots also undergrowth, very white may indicate fully-grown biomass. Overgrowth of mycelium may be indicated by certain other colors such as yellow, brown, gray, orange, pink or red.

[0113] Alternatively, or additionally, the characterization parameter may further comprise a characteristic determined based, at least in part, on the image, such as a maximum size of a crack detected in at least an image of the biomass.

[0114] Alternatively, or additionally, the characterization parameter may comprise an average size of pores in the biomass, such as 10 nm. In exemplary embodiments, the size of pores may range between 2 and 30 nm, preferably between 3 and 25 nm, further preferably between 4 and 20 nm. The size of pores may be determined based, for example, on an image of the biomass. In this case, the skilled person understands that the average pore size may relate only to pores on a surface of the biomass. However, other methods may also be employed to determine pore sizes in an interior of the biomass.

[0115] Alternatively, or additionally, the characterization parameter may comprise a measure of a surface roughness of the biomass. Surface roughness may be indicated, for example, by a measure of a motion of a tactile probe, such as that of an atomic force microscope, or by imaging methods such as scanning electron microscopy. In embodiments, surface roughness may range, for example, from 100 pm to 600 pm.

[0116] The method may comprise sending the value for the control parameter to a display unit.

[0117] The control parameter may comprise any of a humidity, a temperature, a brightness, or a concentration of a gas in the environment in which the biomass is grown.

[0118] The process may comprise a process as described above, wherein the control parameter may comprise the selection of the substrate.

[0119] The process may comprise a process as described above, wherein the control parameter may comprise the selection of a substrate component.

[0120] The process may comprise a process as described above, wherein the control parameter may comprise the defined quantity of the substrate. The process may comprise a process as described above, wherein the control parameter may comprise the species of mycelium.

[0121] The process may comprise a process as described above, wherein the control parameter may comprise the selection of the additive.

[0122] The process may comprise a process as described above, wherein the control parameter may comprise the selection of any of the plurality of additives.

[0123] The process may comprise a process as described above, wherein the control parameter may comprise an energy of the radiation.

[0124] The method may comprise determining a stage of growth of the biomass based, at least in part, on the sensor data.

[0125] The method may comprise determining a value for the control parameter to increase or decrease a rate of growth of the biomass.

[0126] The method may comprise storing an association between the determined value for the control parameter and the sensor data, or the data related, at least in part thereto, based, at least in part, on which the value for the control parameter is determined. In other words, defined sensor data, or data related, at least in part thereto, may be used to determine the value for the control parameter. The method may then comprise storing an association between the defined sensor data, or data related, at least in part, thereto, and the determined value for the control parameter. The stored association may further allow establishment of the, at least substantially, causal relationship between the value(s) for the control parameter(s) and the state of the biomass.

[0127] The method may comprise storing an association between the determined characterization value and the sensor data, or the data related, at least in part thereto, based, at least in part, on which the characterization value is determined.

[0128] The method may further comprise subjecting the biomass to deliberate contamination. Deliberate contamination may be of advantage in generating training data for detecting growth of unwanted micro-organisms. By introducing microbial contaminants, for example mold, at different stages of growth, and observing the resulting biomass at different subsequent stages of growth, the model may be trained to better detect such defects in the biomass.

[0129] Similarly, by varying values for other control parameters of the process, such as humidity, temperature, etc. the growth process can be optimized. The method may comprise varying the values for the control parameters automatically, or at least semi-automatically, and storing the resulting sensor data to generate the training data.

[0130] The method may comprise a computer-implemented method.

[0131] According to a second aspect, the present invention relates to a system for controlling a process of growing a biomass, wherein the system may be configured to: determine a value for a control parameter of the process.

[0132] The process may comprise a process as described above.

[0133] The system may comprise a data processing unit configured to determine the value for the control parameter.

[0134] The system may comprise an actuator configured to change a value for a control parameter of the process.

[0135] The system may comprise a control unit.

[0136] The control unit may be configured to communicate with the data processing unit.

[0137] The control unit may be configured to communicate with the actuator.

[0138] The system, particularly the data processing unit thereof, may be configured to send the value for the control parameter to the control unit.

[0139] Determining the value for the control parameter may comprise using a model.

[0140] The model may comprise, at least in part, a heuristic model.

[0141] The model may comprise, at least in part, an artificial intelligence-based model.

[0142] The artificial intelligence-based model may comprise a trained model.

[0143] The system may be configured to receive the trained model.

[0144] The system may comprise a communication unit.

[0145] The communication unit may be configured to communicate with the data processing unit.

[0146] The system may be configured to receive the trained model by means, at least in part, of the communication unit. The system, particularly the data processing unit thereof, may be configured to generate the trained model, generating the trained model comprising training a model.

[0147] Generating the trained model may comprise training the model, at least in part, using supervised learning.

[0148] Generating the trained model may comprise training the model, at least in part, using unsupervised learning.

[0149] The system may be configured to store the trained model. The system may be appropriately configured therefor. For example, the system may comprise a memory unit that may be configured to communicate with the data processing unit as described above.

[0150] The system may be configured to send the trained model.

[0151] The system may be configured to send the trained model by means, at least in part, of the communication unit.

[0152] The system may comprise a sensor configured to record data, that may be referred to as sensor data.

[0153] The system may be configured to determine the value for the control parameter based, at least in part, on the sensor data.

[0154] The sensor may be configured to communicate with the data processing unit, and wherein the sensor may be configured to send the sensor data, or at least data related thereto, as input to the model.

[0155] The sensor data may be related, at least in part, to a current state of the biomass.

[0156] The system may be configured to determine the value for the control parameter based, at least in part, on an output of the model.

[0157] Training the model may comprise sending labeled data as input to the model, the labeled data comprising a label, wherein the label relates, at least in part, to a desired value for the control parameter.

[0158] Training the model may comprise comparing an output of the model to the label.

[0159] Training the model may comprise updating the model based, at least in part, on a result of comparing the output of the model to the label. The labeled data may comprise data at least similar to the sensor data.

[0160] The system may be configured to store the sensor data. For example, as described above, the sensor data may be stored in a memory unit of the system. Alternatively, or additionally, the sensor data may be stored, at least in part, in an external memory unit with which the system, particularly the communication unit thereof, may communicate. This may be of advantage if a size of the sensor data is larger than a defined threshold.

[0161] The system may be configured to retrieve stored sensor data.

[0162] The stored sensor data may be related, at least in part, to a previous state of the biomass.

[0163] The system may be configured to send the retrieved sensor data, or at least data related thereto, as input to the model.

[0164] Determining the value for the control parameter may be based, at least in part, on sensor data related, at least in part, to a previous state of the biomass.

[0165] The system may be configured to direct a beam of particles at the biomass, or at least a part thereof.

[0166] The sensor may comprise a particle sensor.

[0167] The system may be configured to detect, by means of the particle sensor, particles transmitted and / or reflected by the biomass.

[0168] The sensor may comprise a camera.

[0169] The camera may be configured to send an image, or at least data related thereto, as input to the model.

[0170] The labeled data may comprise an image.

[0171] The label may be related, at least in part, to a crack, a defect, a deformation, or mold in the image.

[0172] The label may be related, at least in part, to a desired value for the control parameter to, at least, mitigate formation of a crack, a defect, a deformation, or mold in the biomass.

[0173] The system may be configured to detect, by means, at least in part, of the model, any of a crack, a defect, a deformation, or mold in the image. The system may be configured, in response to having detected any of a crack, a defect, a deformation, or mold in the image, to determine, by means, at least in part, of the model, a value for the control parameter to, at least, mitigate formation of any of a crack, a defect, a deformation, or mold in the biomass.

[0174] The system may be configured, in response to having detected any of a crack, a defect, a deformation, or mold in the image, to generate a notification.

[0175] The system may be configured to automatically position a source of the particles and / or the particle sensor.

[0176] The system may be configured to use the control unit to position the source of the particles and / or the particle sensor.

[0177] The sensor may comprise a probe.

[0178] The sensor data may be based, at least in part, on a motion of the probe.

[0179] The system may be configured to direct the probe to establish contact with the biomass, or at least a part thereof.

[0180] The system may be configured to automatically directing the probe to establish contact with the biomass, or at least a part thereof.

[0181] Directing the probe may comprise positioning the probe over the biomass, or at least a part thereof.

[0182] The system may be configured to determine a moisture level of the biomass, or at least a part thereof, by means of the sensor.

[0183] The system may be configured to determine a temperature of the biomass, or at least a part thereof, by means of the sensor.

[0184] The system may be configured to determine a pH level of the biomass, or at least a part thereof, by means of the sensor.

[0185] The system may be configured to determine a density of the biomass, or at least a part thereof, by means of the sensor.

[0186] The system may be configured to identify a region of undergrowth in the biomass, or at least a part thereof, by means of the sensor. The sensor may comprise a humidity sensor, and wherein the system may be configured to determine a humidity of an environment in which the biomass is being grown.

[0187] The sensor may comprise a temperature sensor, and wherein the system may be configured to determine a temperature of an environment in which the biomass is being grown.

[0188] The sensor may comprise a concentration sensor, and wherein the system may be configured to determine a concentration of a gas in an environment in which the biomass is being grown.

[0189] The particle sensor may comprise a photon sensor, and wherein the system may be configured to determine a brightness in an environment in which the biomass is being grown.

[0190] The biomass may be characterized by a characterization parameter, the characterization parameter having a characterization value.

[0191] The system may be configured to determining the characterization value of the characterization parameter based, at least in part, on the sensor data.

[0192] The sensor data may comprise a timestamp related, at least in part, to a time at which the sensor data, or at least a part thereof, is recorded.

[0193] The control unit may be configured to control the actuator, and wherein the system may be configured to activate and / or deactivate the actuator based, at least in part, on the value for the control parameter.

[0194] The system may be configured to store the determined value for the control parameter.

[0195] The system may be configured to store a time at which the value for the control parameter is sent to the control unit.

[0196] The system may be configured to provide a desired characterization value for the characterization parameter as input to the model.

[0197] The system may be configured to determine the value for the control parameter based, at least in part, on the desired characterization value.

[0198] The label may be related, at least in part, to a desired value for the control parameter to grow biomass characterized by the characterization parameter of value, at least significantly, identical to the labeled data. The characterization parameter may comprise any of a density, a Young's modulus, a hydrophobicity, a water retention capacity, or an appearance of the biomass.

[0199] The system may be configured to send the value for the control parameter to a display unit.

[0200] The control parameter may comprise any of a humidity, a temperature, a brightness, or a concentration of a gas in the environment in which the biomass is grown.

[0201] The process may comprise a process as described above, wherein the control parameter may comprise the selection of the substrate.

[0202] The process may comprise a process as described above, wherein the control parameter may comprise the selection of a substrate component.

[0203] The process may comprise a process as described above, wherein the control parameter may comprise the defined quantity of the substrate.

[0204] The process may comprise a process as described above, wherein the control parameter may comprise the species of mycelium.

[0205] The process may comprise a process as described above, wherein the control parameter may comprise the selection of the additive.

[0206] The process may comprise a process as described above, wherein the control parameter may comprise the selection of any of the plurality of additives.

[0207] The process may comprise a process as described above, wherein the control parameter may comprise an energy of the radiation.

[0208] The system may be configured to determining a stage of growth of the biomass based, at least in part, on the sensor data.

[0209] The system may be configured to determine a value for the control parameter to increase or decrease a rate of growth of the biomass.

[0210] The system may comprise a queuing unit.

[0211] The queuing unit may be configured to communicate with the data processing unit.

[0212] The queuing unit may be configured to communicate with the control unit. The communication between the data processing unit and the control unit is via the queuing unit.

[0213] The system may be configured to perform the method as described above.

[0214] According to a third aspect, the present invention relates to a use of the system and / or the method as described above to control a process for growing a biomass.

[0215] The process may comprise a process as described above.

[0216] The mycelium may comprise any of Ganoderma lucidum, Ganoderma resinaceum, Ganoderma lingzhi, Ganoderma australe, Fomes fomentarius, Lentinula edodes, Pleurotus eryngii, Pleurotus djamor, Pycnoporus sanguineus, Trametes versicolor, Trametes hirsuta, Agaricus bisporus, Fomes fomentarius, Schizophyllum commune, Pleurotus ostreatus, Pleurotus pulmonarius, Ganoderma applanatum, Tropicoporus linteus, or Laetiporus sulphureus.

[0217] The process may comprise a process as described above, and the use may comprise monitoring any of the growth and the dehydration stages.

[0218] The process may comprise a process as described above, and the use may comprise optimizing any of the growth and the dehydration stages.

[0219] According to a fourth aspect, the present invention relates to a computer program product comprising instructions when run on a data processing unit of a system as described above, to perform the method as described above.

[0220] Below process embodiments will be discussed. These are abbreviated by the letter "P" followed by a number. Whenever reference is herein made to the process embodiments, the following embodiments are meant. Embodiments of the process are only mentioned here to allow easy referencing, but are not to be considered inventive aspects of the present invention. In fact, aspects of the process as described herein are well-known to the skilled person.

[0221] Pl. A process for growing a biomass, wherein the process comprises introducing mycelium into a prepared substrate.

[0222] P2. The process according to the preceding embodiment, wherein the process comprises selecting the substrate.

[0223] P3. The process according to the preceding embodiment, wherein the substrate comprises one or more substrate components, and wherein selecting the substrate comprises selecting any of the one or more substrate components. P4. The process according to any of the 2 preceding embodiments, wherein the process comprises selecting a defined quantity of the substrate such that the mixture comprises a defined fraction of the substrate.

[0224] P5. The process according to any of the preceding process embodiments, wherein the process comprises selecting a species of mycelium.

[0225] P6. The process according to any of the preceding process embodiments, wherein the process comprises adding an additive to the mixture.

[0226] P7. The process according to the preceding embodiment, wherein the process comprises adding a plurality of additives to the mixture.

[0227] P8. The process according to any of the 2 preceding embodiments, wherein the process comprises selecting the additive or any of the plurality of additives to add to the mixture.

[0228] P9. The process according to any of the preceding process embodiments, wherein the process comprises sterilizing the substrate. The substrate may be sterilized prior to adding the fungi and any other components as described above. This may be of advantage in preventing growth of undesired species of micro-organisms in the biomass.

[0229] PIO. The process according to the preceding embodiment, wherein the process further comprises heat-treating, steam / vapor-treating, or UV-treating the substrate.

[0230] Pll. The process according to the preceding embodiment, wherein the process further comprises storing the mixture in a controlled environment, and allowing the biomass to grow for a plurality of days.

[0231] P12. The process according to any of the preceding process embodiments, wherein the process comprises a growth stage, wherein the growth stage comprises a stage of growth of the mycelium.

[0232] P13. The process according to any of the preceding process embodiments, wherein the process comprises a dehydration stage, wherein the dehydration stage comprises dehydrating the biomass.

[0233] P14. The process according to the preceding embodiment, wherein dehydrating the biomass comprises evaporative dehydration.

[0234] P15. The process according to any of the 2 preceding embodiments, wherein dehydrating the biomass comprises irradiating the biomass. P16. The process according to the preceding embodiment, wherein the process comprises irradiating the biomass, at least in part, with microwave radiation.

[0235] P17. The process according to the preceding embodiment, wherein the process comprises irradiating the biomass, at least in part, with infrared radiation.

[0236] P18. The process according to any of the preceding process embodiments and with the features of embodiment P13, wherein dehydrating the biomass comprises using a furnace.

[0237] P19. The process according to any of the preceding process embodiments and with the features of embodiment P13, wherein dehydrating the biomass comprises increasing a temperature of the biomass up to 90°C, preferably up to 100°C, further preferably up to 150°C, yet further preferably up to 230°C.

[0238] P20. The process according to the preceding embodiment, wherein dehydrating the biomass comprises reducing the temperature of the biomass to room temperature.

[0239] P21. The process according to any of the preceding process embodiments and with the features of embodiments P12 and P13, wherein the growth stage is followed by the dehydration stage.

[0240] P22. The process according to any of the preceding process embodiments and with the features of embodiment P13, wherein a result of dehydrating the biomass is, at the end of the dehydration stage, a moisture level of the biomass being in the range defined by 5% and 50%, preferably by 5% and 40%, further preferably by 5% and 30%.

[0241] P23. The process according to any of the preceding process embodiments, wherein a result of the process is, at the end of the process, a pH level of the biomass being in the range defined by 4.5 and 7.5, preferably by 4.8 and 7.2, further preferably by 5 and 7.

[0242] The present invention is also described by the following numbered embodiments.

[0243] Below method embodiments will be discussed. These are abbreviated by the letter "M" followed by a number. Whenever reference is herein made to the method embodiments, the following embodiments are meant.

[0244] Ml. A method for controlling a process of growing a biomass, wherein the method comprises: determining a value for a control parameter of the process.

[0245] M2. The method according to the preceding embodiment, wherein the process comprises a process according to any of the preceding process embodiments. M3. The method according to any of the preceding method embodiments, wherein the method comprises sending the value for the control parameter to a control unit.

[0246] M4. The method according to any of the preceding method embodiments, wherein determining the value for the control parameter comprises using a model.

[0247] M5. The method according to the preceding embodiment, wherein the model comprises, at least in part, a heuristic model.

[0248] M6. The method according to any of the 2 preceding embodiments, wherein the model comprises, at least in part, an artificial intelligence-based model.

[0249] M7. The method according to the preceding embodiment, wherein the artificial intelligencebased model comprises a trained model.

[0250] M8. The method according to the preceding embodiment, wherein the method comprises receiving the trained model.

[0251] M9. The method according to any of the preceding method embodiments and with the features of embodiment M7, but without the features of the preceding embodiment, wherein the method comprises generating the trained model, generating the trained model comprising training a model.

[0252] MIO. The method according to the preceding embodiment, wherein generating the trained model comprises training the model, at least in part, using supervised learning.

[0253] Mil. The method according to any of the 2 preceding embodiments, wherein generating the trained model comprises training the model, at least in part, using unsupervised learning.

[0254] M12. The method according to any of the 3 preceding embodiments, wherein the method comprises storing the trained model.

[0255] M13. The method according to any of the 4 preceding embodiments, wherein the method comprises sending the trained model.

[0256] M14. The method according to any of the preceding method embodiments, wherein the method comprises receiving data from a sensor, that may be referred to as sensor data.

[0257] M15. The method according to the preceding embodiment, wherein the method further comprises receiving data related, at least in part, to the sensor data. M16. The method according to any of the 2 preceding embodiments, wherein the method comprises determining the value for the control parameter based, at least in part, on the sensor data, or the data related, at least in part, thereto.

[0258] M17. The method according to any of the 3 preceding embodiments and with the features of embodiment M3, wherein the method comprises sending the sensor data, or at least data related thereto, as input to the model.

[0259] M18. The method according to any of the 4 preceding embodiments, wherein the sensor data is related, at least in part, to a current state of the biomass.

[0260] M19. The method according to any of the preceding method embodiments and with the features of embodiment M4, wherein determining the value for the control parameter is based, at least in part, on an output of the model.

[0261] M20. The method according to any of the preceding method embodiments and with the features of embodiment MIO, wherein training the model comprises sending labeled data as input to the model, the labeled data comprising a label, wherein the label relates, at least in part, to a desired value for the control parameter.

[0262] M21. The method according to the preceding embodiment, wherein training the model comprises comparing an output of the model to the label.

[0263] M22. The method according to the preceding embodiment, wherein training the model comprises updating the model based, at least in part, on a result of comparing the output of the model to the label.

[0264] M23. The method according to any of the 3 preceding embodiments and with the features of embodiment M14, wherein the labeled data comprises data at least similarto the sensor data.

[0265] M24. The method according to any of the preceding method embodiments and with the features of embodiment M14, wherein the method comprises storing the sensor data.

[0266] M25. The method according to any of the preceding method embodiments and with the features of embodiment M14, wherein the method comprises retrieving stored sensor data.

[0267] M26. The method according to the preceding embodiment, wherein the stored sensor data is related, at least in part, to a previous state of the biomass.

[0268] M27. The method according to any of the 2 preceding embodiments and with the features of embodiment M4, wherein the method comprises sending the retrieved sensor data, or at least data related thereto, as input to the model. M28. The method according to any of the preceding method embodiments, wherein determining the value for the control parameter is based, at least in part, on sensor data related, at least in part, to a previous state of the biomass.

[0269] M29. The method according to any of the preceding method embodiments, wherein the method comprises directing a beam of particles at the biomass, or at least a part thereof.

[0270] M30. The method according to any of the preceding method embodiments and with the features of embodiment M14, wherein the sensor comprises a particle sensor.

[0271] M31. The method according to the preceding embodiment and with the features of embodiment M29, wherein the method comprises detecting, using the particle sensor, particles transmitted and / or reflected by the biomass.

[0272] M32. The method according to any of the 2 preceding embodiments, wherein the sensor comprises a camera.

[0273] M33. The method according to any of the preceding method embodiments and with the features of embodiment M30, wherein the particle sensor comprises a photon sensor, and wherein the photon sensor is configured to sense photons with a wavelength in the range defined by 200 nm and 2500 nm, preferably by 300 nm and 2000 nm, further preferably by 400 nm and 1500 nm and / or wherein the photon sensor is configured to sense photons with a wavelength in the range defined by 2000 nm and 15000 nm, preferably by 3000 nm and 14000 nm, further preferably by 8000 nm and 14000 nm.

[0274] M34. The method according to any of the preceding method embodiments and with the features of embodiment M32, wherein the data received from the camera comprises an image.

[0275] M35. The method according to any of the preceding method embodiments and with the features of embodiments M23, and M32, wherein the labeled data comprises an image.

[0276] M36. The method according to the preceding embodiment, wherein the label is related, at least in part, to a crack, a defect, a deformation, or contamination in the image.

[0277] M37. The method according to any of the 2 preceding embodiments, wherein the label is related, at least in part, to a desired value for the control parameter to, at least, mitigate formation of a crack, a defect, a deformation, or contamination in the biomass.

[0278] M38. The method according to any of the 4 preceding embodiments and with the features of embodiment M4, wherein the method comprises detecting, using, at least in part, the model, any of a crack, a defect, a deformation, or contamination in the image. M39. The method according to the preceding embodiment, wherein the method comprises, in response to having detected any of a crack, a defect, a deformation, or contamination in the image, determining, using, at least in part, the model, a value for the control parameter to, at least, mitigate formation of any of a crack, a defect, a deformation, or contamination in the biomass.

[0279] M40. The method according to any of the preceding method embodiments and with the features of embodiment M38, wherein the method comprises, in response to having detected any of a crack, a defect, a deformation, or contamination in the image, generating a notification.

[0280] M41. The method according to any of the preceding method embodiments and with the features of any of embodiments M29, and M30, wherein the method comprises automatically positioning a source of the particles and / or the particle sensor.

[0281] M42. The method according to the preceding embodiment and with the features of embodiment M2, wherein the method comprises using the control unit to position the source of the particles and / or the particle sensor.

[0282] M43. The method according to any of the preceding method embodiments and with the features of embodiment M14, wherein the sensor comprises a probe.

[0283] M44. The method according to the preceding embodiment, wherein the sensor data is based, at least in part, on a motion of the probe.

[0284] M45. The method according to any of the 2 preceding embodiments, wherein the method comprises directing the probe to establish contact with the biomass, or at least a part thereof.

[0285] M46. The method according to the preceding embodiment, wherein the method comprises automatically directing the probe to establish contact with the biomass, or at least a part thereof.

[0286] M47. The method according to any of the 2 preceding embodiments, wherein directing the probe comprises positioning the probe over the biomass, or at least a part thereof.

[0287] M48. The method according to any of the preceding method embodiments and with the features of embodiment M14, wherein the method comprises using the sensor to determine a moisture level of the biomass, or at least a part thereof. M49. The method according to any of the preceding method embodiments and with the features of embodiment M14, wherein the method comprises using the sensor to determine a temperature of the biomass, or at least a part thereof.

[0288] M50. The method according to any of the preceding method embodiments and with the features of embodiment M14, wherein the method comprises using the sensor to determine a pH level of the biomass, or at least a part thereof.

[0289] M51. The method according to any of the preceding method embodiments and with the features of embodiment M14, wherein the method comprises using the sensor to determine a density of the biomass, or at least a part thereof.

[0290] M52. The method according to any of the preceding method embodiments and with the features of embodiment M14, wherein the method comprises using the sensor to identify a region of undergrowth or overgrowth in the biomass, or at least a part thereof.

[0291] M53. The method according to any of the preceding method embodiments and with the features of embodiment M14, wherein the sensor comprises a humidity sensor, and wherein the method comprises determining a humidity of an environment in which the biomass is being grown and / or dehydrated.

[0292] M54. The method according to any of the preceding method embodiments and with the features of embodiment M14, wherein the sensor comprises a temperature sensor, and wherein the method comprises determining a temperature of an environment in which the biomass is being grown and / or dehydrated.

[0293] M55. The method according to any of the preceding method embodiments and with the features of embodiment M14, wherein the sensor comprises a concentration sensor, and wherein the method comprises determining a concentration of a gas in an environment in which the biomass is being grown and / or dehydrated.

[0294] M56. The method according to any of the preceding method embodiments and with the features of embodiment M30, wherein the particle sensor comprises a photon sensor, and wherein the method comprises determining a brightness in an environment in which the biomass is being grown and / or dehydrated.

[0295] M57. The method according to any of the preceding method embodiments, wherein the biomass is characterized by a characterization parameter, the characterization parameter having a characterization value.

[0296] M58. The method according to the preceding embodiment and with the features of any of embodiments M14, and M15, wherein the method comprises determining the characterization value of the characterization parameter based, at least in part, on the sensor data, or the data related, at least in part, thereto.

[0297] M59. The method according to any of the preceding method embodiments and with the features of embodiment M15, wherein the data related, at least in part, to the sensor data comprises a timestamp related, at least in part, to a time at which the sensor data, or at least a part thereof, is recorded.

[0298] M60. The method according to any of the preceding method embodiments and with the features of embodiment M3, wherein the control unit is configured to control an actuator, and wherein the method comprises activating and / or deactivating the actuator based, at least in part, on the value for the control parameter.

[0299] M61. The method according to any of the preceding method embodiments, wherein the method comprises storing the determined value for the control parameter.

[0300] M62. The method according to the preceding embodiment and with the features of embodiment M2, wherein the method comprises storing a time at which the value for the control parameter is sent to the control unit.

[0301] M63. The method according to any of the preceding method embodiments and with the features of embodiments M4, and M57, wherein the method comprises providing a desired characterization value for the characterization parameter as input to the model.

[0302] M64. The method according to the preceding embodiment, wherein the method comprises determining the value for the control parameter based, at least in part, on the desired characterization value.

[0303] M65. The method according to any of the preceding method embodiments and with the features of embodiments M20, and M57, wherein the labeled data comprises data, at least, similar to the characterization value.

[0304] M66. The method according to the preceding embodiment, wherein the label is related, at least in part, to a desired value for the control parameter to grow biomass characterized by the characterization parameter of value, at least significantly, identical to the labeled data.

[0305] M67. The method according to any of the preceding embodiments and with the features of embodiment M57, wherein the characterization parameter comprises any of a density, a Young's modulus, a hydrophobicity, a water retention capacity, or an appearance of the biomass. M68. The method according to any of the preceding method embodiments, wherein the method comprises sending the value for the control parameter to a display unit.

[0306] M69. The method according to any of the preceding method embodiments, wherein the control parameter comprises any of a humidity, a temperature, a brightness, or a concentration of a gas in the environment in which the biomass is grown.

[0307] M70. The method according to any of the preceding method embodiments, wherein the process comprises a process according to embodiment P2, wherein the control parameter comprises the selection of the substrate.

[0308] M71. The method according to any of the preceding method embodiments, wherein the process comprises a process according to embodiment P3, wherein the control parameter comprises the selection of a substrate component.

[0309] M72. The method according to any of the preceding method embodiments, wherein the process comprises a process according to embodiment P4, wherein the control parameter comprises the defined quantity of the substrate.

[0310] M73. The method according to any of the preceding method embodiments, wherein the process comprises a process according to embodiment P5, wherein the control parameter comprises the species of mycelium.

[0311] M74. The method according to any of the preceding method embodiments, wherein the process comprises a process according to embodiment P6, wherein the control parameter comprises the selection of the additive.

[0312] M75. The method according to any of the preceding method embodiments, wherein the process comprises a process according to embodiment P7, wherein the control parameter comprises the selection of any of the plurality of additives.

[0313] M76. The method according to any of the preceding method embodiments, wherein the process comprises a process according to embodiment P15, wherein the control parameter comprises an energy of the radiation.

[0314] M77. The method according to any of the preceding method embodiments and with the features of embodiment M14, wherein the method comprises determining a stage of growth of the biomass based, at least in part, on the sensor data.

[0315] M78. The method according to the preceding embodiment, wherein the method comprises determining a value for the control parameter to increase or decrease a rate of growth of the biomass. M79. The method according to any of the preceding method embodiments and with the features of embodiment M16, wherein the method comprises storing an association between the determined value for the control parameter and the sensor data, or the data related, at least in part thereto, based, at least in part, on which the value for the control parameter is determined.

[0316] M80. The method according to any of the preceding method embodiments and with the features of embodiment M58, wherein the method comprises storing an association between the determined characterization value and the sensor data, or the data related, at least in part thereto, based, at least in part, on which the characterization value is determined.

[0317] M81. The method according to any of the preceding method embodiments, wherein the method further comprises injecting mold into the biomass.

[0318] M82. The method according to any of the preceding method embodiments, wherein the method comprises a computer-implemented method.

[0319] Below system embodiments will be discussed. These are abbreviated by the letter "S" followed by a number. Whenever reference is herein made to the "system embodiments", the following embodiments are meant.

[0320] 51. A system for controlling a process of growing a biomass, wherein the system is configured to: determine a value for a control parameter of the process.

[0321] 52. The system according to the preceding embodiment, wherein the process comprises a process according to any of the preceding process embodiments.

[0322] 53. The system according to any of the preceding system embodiments, wherein the system comprises a data processing unit configured to determine the value for the control parameter.

[0323] 54. The system according to any of the preceding system embodiments, wherein the system comprises an actuator configured to change a value for a control parameter of the process.

[0324] 55. The system according to any of the preceding system embodiments, wherein the system comprises a control unit. 56. The system according to the preceding embodiment and with the features of embodiment S3, wherein the control unit is configured to communicate with the data processing unit.

[0325] 57. The system according to any of the 2 preceding embodiments and with the features of embodiment S4, wherein the control unit is configured to communicate with the actuator.

[0326] 58. The system according to any of the preceding system embodiments and with the features of embodiment S5, optionally with the features of embodiment S3, wherein the system, particularly the data processing unit thereof, is configured to send the value for the control parameter to the control unit.

[0327] 59. The system according to any of the preceding system embodiments, wherein determining the value for the control parameter comprises using a model.

[0328] 510. The system according to the preceding embodiment, wherein the model comprises, at least in part, a heuristic model.

[0329] 511. The system according to any of the 2 preceding embodiments, wherein the model comprises, at least in part, an artificial intelligence-based model.

[0330] 512. The system according to the preceding embodiment, wherein the artificial intelligencebased model comprises a trained model.

[0331] 513. The system according to the preceding embodiment, wherein the system is configured to receive the trained model.

[0332] 514. The system according to any of the preceding system embodiments, wherein the system comprises a communication unit.

[0333] 515. The system according to the preceding embodiment and with the features of embodiment S3, wherein the communication unit is configured to communicate with the data processing unit.

[0334] 516. The system according to any of the 2 preceding embodiments and with the features of embodiment S13, wherein the system is configured to receive the trained model by means, at least in part, of the communication unit.

[0335] 517. The system according to any of the preceding system embodiments and with the features of embodiments S3, and S12, but without the features of the preceding embodiment, wherein the system, particularly the data processing unit thereof, is configured to generate the trained model, generating the trained model comprising training a model. 518. The system according to the preceding embodiment, wherein generating the trained model comprises training the model, at least in part, using supervised learning.

[0336] 519. The system according to any of the 2 preceding embodiments, wherein generating the trained model comprises training the model, at least in part, using unsupervised learning.

[0337] 520. The system according to any of the 3 preceding embodiments, wherein the system is configured to store the trained model.

[0338] 521. The system according to any of the 4 preceding embodiments, wherein the system is configured to send the trained model.

[0339] 522. The system according to the preceding embodiment and with the features of embodiment S15, wherein the system is configured to send the trained model by means, at least in part, of the communication unit.

[0340] 523. The system according to any of the preceding system embodiments, wherein the system comprises a sensor configured to record data, that may be referred to as sensor data.

[0341] 524. The system according to the preceding embodiment, wherein the system is configured to determine the value for the control parameter based, at least in part, on the sensor data.

[0342] 525. The system according to any of the 2 preceding embodiments and with the features of embodiments S3, and S9, wherein the sensor is configured to communicate with the data processing unit, and wherein the sensor is configured to send the sensor data, or at least data related thereto, as input to the model.

[0343] 526. The system according to any of the 3 preceding embodiments, wherein the sensor data is related, at least in part, to a current state of the biomass.

[0344] 527. The system according to any of the preceding system embodiments and with the features of embodiment S9, wherein the system is configured to determine the value for the control parameter based, at least in part, on an output of the model.

[0345] 528. The system according to any of the preceding system embodiments and with the features of embodiment S18, wherein training the model comprises sending labeled data as input to the model, the labeled data comprising a label, wherein the label relates, at least in part, to a desired value for the control parameter.

[0346] S29. The system according to the preceding embodiment, wherein training the model comprises comparing an output of the model to the label. 530. The system according to the preceding embodiment, wherein training the model comprises updating the model based, at least in part, on a result of comparing the output of the model to the label.

[0347] 531. The system according to any of the 3 preceding embodiments and with the features of embodiment S23, wherein the labeled data comprises data at least similar to the sensor data.

[0348] 532. The system according to any of the preceding system embodiments and with the features of embodiment S23, wherein the system is configured to store the sensor data.

[0349] 533. The system according to any of the preceding system embodiments and with the features of embodiment S23, wherein the system is configured to retrieve stored sensor data.

[0350] 534. The system according to the preceding embodiment, wherein the stored sensor data is related, at least in part, to a previous state of the biomass.

[0351] 535. The system according to any of the 2 preceding embodiments and with the features of embodiment S9, wherein the system is configured to send the retrieved sensor data, or at least data related thereto, as input to the model.

[0352] 536. The system according to any of the preceding system embodiments, wherein determining the value for the control parameter is based, at least in part, on sensor data related, at least in part, to a previous state of the biomass.

[0353] 537. The system according to any of the preceding system embodiments, wherein the system is configured to direct a beam of particles at the biomass, or at least a part thereof.

[0354] 538. The system according to any of the preceding system embodiments and with the features of embodiment S23, wherein the sensor comprises a particle sensor.

[0355] 539. The system according to the preceding embodiment and with the features of embodiment S37, wherein the system is configured to detect, by means of the particle sensor, particles transmitted and / or reflected by the biomass.

[0356] 540. The system according to any of the 2 preceding embodiments, wherein the sensor comprises a camera.

[0357] 541. The system according to any of the preceding system embodiments and with the features of embodiment S38, wherein the particle sensor comprises a photon sensor, and wherein the photon sensor is configured to sense photons with a wavelength in the range defined by 200 nm and 2500 nm, preferably by 300 nm and 2000 nm, further preferably by 400 nm and 1500 nm and / or wherein the photon sensor is configured to sense photons with a wavelength in the range defined by 2000 nm and 15000 nm, preferably by 3000 nm and 14000 nm, further preferably by 8000 nm and 14000 nm.

[0358] 542. The system according to any of the preceding system embodiments and with the features of embodiments S25, and S40, wherein the camera is configured to send an image, or at least data related thereto, as input to the model.

[0359] 543. The system according to any of the preceding system embodiments and with the features of embodiments S31, and S40, wherein the labeled data comprises an image.

[0360] 544. The system according to the preceding embodiment, wherein the label is related, at least in part, to a crack, a defect, a deformation, or contamination in the image.

[0361] 545. The system according to any of the 2 preceding embodiments, wherein the label is related, at least in part, to a desired value for the control parameter to, at least, mitigate formation of a crack, a defect, a deformation, or contamination in the biomass.

[0362] 546. The system according to any of the 4 preceding embodiments and with the features of embodiment S9, wherein the system is configured to detect, by means, at least in part, of the model, any of a crack, a defect, a deformation, or contamination in the image.

[0363] 547. The system according to the preceding embodiment, wherein the system is configured, in response to having detected any of a crack, a defect, a deformation, or contamination in the image, to determine, by means, at least in part, of the model, a value for the control parameter to, at least, mitigate formation of any of a crack, a defect, a deformation, or contamination in the biomass.

[0364] 548. The system according to any of the preceding system embodiments and with the features of embodiment S46, wherein the system is configured, in response to having detected any of a crack, a defect, a deformation, or contamination in the image, to generate a notification.

[0365] 549. The system according to any of the preceding system embodiments and with the features of any of embodiments S37, and S38, wherein the system is configured to automatically position a source of the particles and / or the particle sensor.

[0366] S50. The system according to the preceding embodiment and with the features of embodiment S8, wherein the system is configured to use the control unit to position the source of the particles and / or the particle sensor. 551. The system according to any of the preceding system embodiments and with the features of embodiment S23, wherein the sensor comprises a probe.

[0367] 552. The system according to the preceding embodiment, wherein the sensor data is based, at least in part, on a motion of the probe.

[0368] 553. The system according to any of the 2 preceding embodiments, wherein the system is configured to direct the probe to establish contact with the biomass, or at least a part thereof.

[0369] 554. The system according to the preceding embodiment, wherein the system is configured to automatically directing the probe to establish contact with the biomass, or at least a part thereof.

[0370] 555. The system according to any of the 2 preceding embodiments, wherein directing the probe comprises positioning the probe over the biomass, or at least a part thereof.

[0371] 556. The system according to any of the preceding system embodiments and with the features of embodiment S23, wherein the system is configured to determine a moisture level of the biomass, or at least a part thereof, by means of the sensor.

[0372] 557. The system according to any of the preceding system embodiments and with the features of embodiment S23, wherein the system is configured to determine a temperature of the biomass, or at least a part thereof, by means of the sensor.

[0373] 558. The system according to any of the preceding system embodiments and with the features of embodiment S23, wherein the system is configured to determine a pH level of the biomass, or at least a part thereof, by means of the sensor.

[0374] 559. The system according to any of the preceding system embodiments and with the features of embodiment S23, wherein the system is configured to determine a density of the biomass, or at least a part thereof, by means of the sensor.

[0375] 560. The system according to any of the preceding system embodiments and with the features of embodiment S23, wherein the system is configured to identify a region of undergrowth in the biomass, or at least a part thereof, by means of the sensor.

[0376] 561. The system according to any of the preceding system embodiments and with the features of embodiment S23, wherein the sensor comprises a humidity sensor, and wherein the system is configured to determine a humidity of an environment in which the biomass is being grown. 562. The system according to any of the preceding system embodiments and with the features of embodiment S23, wherein the sensor comprises a temperature sensor, and wherein the system is configured to determine a temperature of an environment in which the biomass is being grown.

[0377] 563. The system according to any of the preceding system embodiments and with the features of embodiment S23, wherein the sensor comprises a concentration sensor, and wherein the system is configured to determine a concentration of a gas in an environment in which the biomass is being grown.

[0378] 564. The system according to any of the preceding system embodiments and with the features of embodiment S38, wherein the particle sensor comprises a photon sensor, and wherein the system is configured to determine a brightness in an environment in which the biomass is being grown.

[0379] 565. The system according to any of the preceding system embodiments, wherein the biomass is characterized by a characterization parameter, the characterization parameter having a characterization value.

[0380] 566. The system according to the preceding embodiment and with the features of embodiment S23, wherein the system is configured to determining the characterization value of the characterization parameter based, at least in part, on the sensor data.

[0381] 567. The system according to any of the preceding system embodiments and with the features of embodiment S23, wherein the sensor data comprises a timestamp related, at least in part, to a time at which the sensor data, or at least a part thereof, is recorded.

[0382] 568. The system according to any of the preceding system embodiments and with the features of embodiment S7, wherein the control unit is configured to control the actuator, and wherein the system is configured to activate and / or deactivate the actuator based, at least in part, on the value for the control parameter.

[0383] 569. The system according to any of the preceding system embodiments, wherein the system is configured to store the determined value for the control parameter.

[0384] 570. The system according to the preceding embodiment and with the features of embodiment S8, wherein the system is configured to store a time at which the value for the control parameter is sent to the control unit.

[0385] S71. The system according to any of the preceding system embodiments and with the features of embodiments S9, and S65, wherein the system is configured to provide a desired characterization value for the characterization parameter as input to the model. 572. The system according to the preceding embodiment, wherein the system is configured to determine the value for the control parameter based, at least in part, on the desired characterization value.

[0386] 573. The system according to any of the preceding system embodiments and with the features of embodiments S28, and S65, wherein the labeled data comprises data, at least, similar to the characterization value.

[0387] 574. The system according to the preceding embodiment, wherein the label is related, at least in part, to a desired value for the control parameter to grow biomass characterized by the characterization parameter of value, at least significantly, identical to the labeled data.

[0388] 575. The system according to any of the preceding embodiments and with the features of embodiment S65, wherein the characterization parameter comprises any of a density, a Young's modulus, a hydrophobicity, a water retention capacity, or an appearance of the biomass.

[0389] 576. The system according to any of the preceding system embodiments, wherein the system is configured to send the value for the control parameter to a display unit.

[0390] 577. The system according to any of the preceding system embodiments, wherein the control parameter comprises any of a humidity, a temperature, a brightness, or a concentration of a gas in the environment in which the biomass is grown.

[0391] 578. The system according to any of the preceding system embodiments, wherein the process comprises a process according to embodiment P2, wherein the control parameter comprises the selection of the substrate.

[0392] 579. The system according to any of the preceding system embodiments, wherein the process comprises a process according to embodiment P3, wherein the control parameter comprises the selection of a substrate component.

[0393] 580. The system according to any of the preceding system embodiments, wherein the process comprises a process according to embodiment P4, wherein the control parameter comprises the defined quantity of the substrate.

[0394] 581. The system according to any of the preceding system embodiments, wherein the process comprises a process according to embodiment P5, wherein the control parameter comprises the species of mycelium. 582. The system according to any of the preceding system embodiments, wherein the process comprises a process according to embodiment P6, wherein the control parameter comprises the selection of the additive.

[0395] 583. The system according to any of the preceding system embodiments, wherein the process comprises a process according to embodiment P7, wherein the control parameter comprises the selection of any of the plurality of additives.

[0396] 584. The system according to any of the preceding system embodiments, wherein the process comprises a process according to embodiment P15, wherein the control parameter comprises an energy of the radiation.

[0397] 585. The system according to any of the preceding system embodiments and with the features of embodiment S23, wherein the system is configured to determining a stage of growth of the biomass based, at least in part, on the sensor data.

[0398] 586. The system according to the preceding embodiment, wherein the system is configured to determine a value for the control parameter to increase or decrease a rate of growth of the biomass.

[0399] 587. The system according to any of the preceding system embodiments, wherein the system comprises a queuing unit.

[0400] 588. The system according to the preceding embodiment and with the features of embodiment S3, wherein the queuing unit is configured to communicate with the data processing unit.

[0401] 589. The system according to any of the 2 preceding embodiments and with the features of embodiment S5, wherein the queuing unit is configured to communicate with the control unit.

[0402] 590. The system according to the preceding embodiment and with the features of embodiments S6, and S88, wherein the communication between the data processing unit and the control unit is via the queuing unit.

[0403] 591. The system according to any of the preceding system embodiments, wherein the system is configured to perform the method according to any of the preceding method embodiments.

[0404] Below use embodiments will be discussed. These are abbreviated by the letter "U" followed by a number. Whenever reference is herein made to the "use embodiments", the following embodiments are meant. Ul. A use of the system and / or the method according to any of the preceding system and / or method embodiments respectively to control a process for growing a biomass.

[0405] U2. The use according to the preceding embodiment, wherein the process comprises a process according to any of the preceding process embodiments.

[0406] U3. The use according to the preceding embodiment, wherein the mycelium comprises any of Ganoderma lucidum, Ganoderma resinaceum, Ganoderma lingzhi, Ganoderma australe, Fomes fomentarius, Lentinula edodes, Pleurotus eryngii, Pleurotus djamor, Pycnoporus sanguineus, Trametes versicolor, Trametes hirsute, Agaricus bisporus, Fomes fomentarius, Schizophyllum commune, Ganoderma applanatum, Pleurotus osteratus, Pleurotus pulmonarius, Tropicoporus linteus, or Laetiporus sulphureus.

[0407] U4. The use according to the preceding embodiment, wherein the process comprises a process according to any of embodiments P12, and P13, and wherein the use comprises monitoring any of the growth and the dehydration stages.

[0408] U5. The use according to any of the 2 preceding embodiments, wherein the process comprises a process according to any of embodiments P12, and P13, and wherein the use comprises optimizing any of the growth and the dehydration stages.

[0409] Below computer program product embodiments will be discussed. These are abbreviated by the letter "C" followed by a number. Whenever reference is herein made to the "computer program product embodiments", the following embodiments are meant.

[0410] Cl. A computer program product comprising instructions when run on a data processing unit of a system according to any of the preceding system embodiments, to perform the method according to any of the preceding method embodiments.

[0411] Brief Figure Description

[0412] Figure 1 depicts an embodiment of a system for controlling a process of growing a biomass.

[0413] Detailed Figure Description

[0414] Figure 1 depicts a system 1 for controlling a process of growing a biomass. The biomass may comprise mycelium and may be used for manufacturing, for example, noise and / or heat insulation panels that may be used in the construction industry. The process may comprise a plurality of steps. First, a substrate may be selected. The substrate may comprise any organic matter. For example, the substrate may comprise wood, or a plant-based material.

[0415] In a next step, a species of mycelium may be selected. The species may comprise a species from any of Ganoderma, Fomes, Pleurotus, or Trametes genera. The selected species of mycelium may then be brought into contact with the substrate to form a mixture. The biomass may be produced by the growth of mycelium in the substrate.

[0416] Once the mycelium has grown to a desired stage, the biomass may be dehydrated to arrive at a defined remaining moisture level that may then be used to manufacture, for example, panels as described above.

[0417] The system 1 may be of particular advantage in monitoring and / or controlling the process as described above. In particular, the system 1 may be of advantage in optimizing the growth of the biomass. Different parameters of the process that may be monitored and / or controlled will be described in further detail below.

[0418] Figure 1 shows different components of system 1 that may be of advantage in monitoring and / or controlling the process. The system 1 may, in particular, comprise a data processing unit 10. The data processing unit 10 may be configured to determine a value for a control parameter of the process. For example, the control parameter may comprise a temperature of a space or, generally, environment, in which the biomass is grown and the data processing unit 10 may be configured to determine a value for the temperature. The value for the control parameter may be of advantage in allowing the system 1 to control the process.

[0419] The system 1 may further comprise a control unit 20. The control unit 20 may be configured to communicate, i.e., exchange data, with the data processing unit 10. In particular, the control unit 20 may be configured to receive data from the data processing unit 10. The data may be received via an intermediary component, such as a queuing unit 90, as described further below. Alternatively, or additionally, the data may be received directly from the data processing unit 10 without an intermediary component.

[0420] The data received from the data processing unit 10 may be identical or at least related, at least in part, to the value of the control parameter determined by the data processing unit 10.

[0421] The control unit 20 may be configured to control an actuator 30 that may be configured to change a control parameter of the process. For example, the control unit 20 may be configured to change a temperature of the environment in which the biomass is being grown by, for example, increasing a power of a heater deployed in the environment. The actuator 30 may control any of a heater, a cooling system, a ventilator, a light, a gas exchange system, a humidifier, or a dehumidifier. The control unit 20 may be configured to control the actuator 30 in response, at least in part, to receiving the data from the data processing unit 10. For example, the data processing unit 10 may determine that a humidity (relative or absolute) of the environment is to be increased to 80%. The data processing unit 10 may send the value 80% to the control unit 20 that may be configured, in response, to control an appropriate actuator 30 to increase the humidity to 80%. For example, the actuator 30 may control a humidifier and may activate the humidifier.

[0422] The system 1 may further comprise a sensor 40. The sensor 40 may be of advantage, for example, in determining if the value of the control parameter determined by the data processing unit 10 has been reached. For example, the sensor 40 may be configured to measure a humidity of the environment and may be of advantage in determining if 80% humidity has been reached.

[0423] The sensor data may be related, at least in part, to a current state of the biomass. As the biomass grows, the state of the biomass may be understood to change and the variation in the state may be recorded by the sensor 40.

[0424] The sensor 40 may be configured to communicate with the data processing unit 10. In particular, the sensor 40 may be configured to send data to the data processing unit 10.

[0425] The sensor 40 may be configured to record data, that may be referred to as sensor data. The sensor 40 may be configured to send the sensor data to the data processing unit 10. The system 1 may be configured to determine the value of the control parameter based, at least in part, on the sensor data, or data related thereto.

[0426] The system 1 may comprise a memory unit 60. Alternatively, or additionally, the system 1 may be configured to communicate with an external memory unit 60 such as an external database. The memory unit 60 may be of advantage in storing various data that may be used by the system 1 to determine the value for the control parameter.

[0427] The system 1 may be configured to store the sensor data, or at least a part thereof, and / or data related thereto. The system 1 may be configured to store, for example, a time associated with the sensor data. The time may comprise a time at which the sensor data was recorded and / or a time at which the sensor data was sent by the sensor 40 and / or a time at which the sensor data was received by the data processing unit 10. Thus, generally, a variation of the recorded sensor data over time may be stored that may correspond, at least significantly, to a variation in the state of the biomass over time.

[0428] The system 1 may be configured to store the determined value for the control parameter. As described above, the system 1 may be configured to determine the value for the control parameter based, at least in part, on the sensor data, or data related thereto. The system 1 may be further configured to store an association between the determined value of the control parameter and the sensor data based, at least in part, on which the value of the control parameter has been determined. Thus, generally, a relationship between the recorded sensor data and the value(s) of the control parameter(s) determined based, at least in part, thereon may be stored. The relationship so stored may be of advantage in controlling the process of growing the biomass as described further below.

[0429] The system 1 may further comprise a communication unit 50. The communication unit 50 may facilitate communication between any two units of the system 1 as described above. For example, the sensor 40 may send the sensor data to the communication 50 that may, in turn, send the sensor data to the data processing unit 10.

[0430] The communication unit 50 may, however, be of particular advantage in communicating with an external device. For example, the external device may comprise a remote server and / or a remote database. Communication with the external device may be achieved wirelessly or by means of a wire.

[0431] The system 1 may further comprise a queuing unit 90. Queuing unit 90 may, in some embodiments, as depicted in Figure 1, be implemented in the communication unit 50. However, it may be understood, that the queuing unit 90 may also be implemented as a separate unit.

[0432] The queuing unit 90 may facilitate asynchronous exchange of data between different units of the system 1. In other words, the data exchange between different units of the system 1 may be mediated via the queuing unit 90. It may be understood, that the different units of the system 1 may, thus, be configured to send data to the queuing unit 90, and the queuing unit 90 may be configured to send the data to the corresponding receiving unit. For example, the data processing unit 10 may send the value of the control parameter to the queuing unit 90 and the queuing unit 90 may send the value to the control unit 20.

[0433] The queuing unit 90 may be of particular advantage in enhancing a robustness of the system 1 to network outages. For example, the different units of the system 1 may be arranged so that communication between the sensor 40 and the data processing unit 10 may be a wired connection (comprised in the same device, for example), whereas communication between the control unit 20 and the data processing unit 10 may be a wireless connection. The wireless connection may be less reliable than the wired connection, and may break intermittently. Then, the queuing unit 90 may store the value(s) of the control parameter(s) until the wireless connection is (re-)established to send the value(s) to the control unit 20. The system 1 may preferably comprise a plurality of sensors 40. The queuing unit 90 may be of particular advantage in embodiments of the system 1 with a plurality of sensors 40. In particular, the different sensors 40 in the plurality of sensors 40 may be configured to record sensor data at different rates. The different sensors 40 may then send the recorded sensor data at different times to the queuing unit 90 that may be configured to store the data until there is bandwidth available to send it to the data processing unit 10.

[0434] Thus, embodiments of the system 1 may allow a feedback loop to be established that may allow sensing a property of the biomass or the environment that it is grown in, to determine a value of a control parameter, and to change a control parameter of the process to optimize the growth of the biomass.

[0435] The sensor 40 may be configured to record a characteristic of an environment in which the biomass is being grown. In particular, the sensor 40 may record any of a humidity, a temperature, a concentration of a component or a gas, or an ambient brightness of / in an environment of the biomass; for example, the sensor 40 may record the humidity in a room in which the biomass is being grown.

[0436] The sensor 40 may be configured to record a characteristic of the biomass itself. In particular, the sensor 40 may be configured to record an appearance and / or a thermal property of the biomass by means, for example, of a photon sensor or a camera. The photon sensor or camera may be configured to detect photons of optical wavelength, but also, for example, of infrared wavelength. Generally, the photon sensor or the camera may be configured to detect radiation with a wavelength in the range defined by 300 nm and 1500 nm, preferably by 400 nm and 1400 nm, further preferably by 450 nm and 1350 nm.

[0437] Further particularly, the sensor 40 may be configured to record a density, and / or a change thereof, of the biomass during the growth or dehydration stage. For example, the density may comprise an areal density and may be measured by measuring a weight of piece and an area of the piece in manufacturing. Alternatively, or additionally, any other suitable method of measuring the density in the manufacturing process may be employed.

[0438] The sensor 40 may be configured to record a density of the mycelial network in the biomass. As described above, when mycelium is mixed together with a substrate, mycelium grows to fill out spaces by drawing nutrition from the substrate. The greater the density of the mycelial network in the biomass, the greater may be a strength of a panel manufactured from the biomass. Thus, recording a density of the mycelial network may be particularly advantageous. Density of the mycelial network may be recorded, for example, based, at least in part, on an image of the biomass. For example, the image of the biomass may be processed to determine regions (pixels) of the image with a brightness or detected energy greater than a defined threshold. A greater value may indicate a region where mycelium has grown whereas a lower density may indicate, at least substantially, an empty region. Additionally, or alternatively, growth density, specifically the proliferation of mycelium during the growth stage may be measured via thermal imaging. Alternatively, density can be measured via measuring mycelium network density by microscopy, preferably using SEM imaging. Additionally, or alternatively, any other suitable method of measuring the mycelium network density in the biomass may be employed.

[0439] The sensor 40 may be configured to record a moisture level of the biomass. The moisture level may be expressed as a weight percent - for example, 80% by weight of the biomass implying that 80% of the weight of the biomass is contained as water. A moisture level greater than about 50 - 60% by weight may promote the growth of mycelium. Thus, it may be of advantage to keep the moisture level greater than about 50 - 60% by weight in a growth stage of the process, whereas it may be of advantage to keep the moisture level lower than 50% after dehydration to prevent further growth of mycelium. Thus, generally, it may be of advantage to monitor the moisture level of the biomass. Moisture level may be measured, for example, by means of moisture or humidity sensors located in the growing biomass, or remotely, through non-contact sensors.

[0440] The moisture level recorded by the sensor 40 may be used to determine, for example, a rate of dehydration of the biomass in the dehydration stage. For example, the sensor 40 may record the moisture level at different times. The rate of dehydration may then be estimated based, at least in part, on the measured moisture levels and the times at which they are measured, for example, by interpolation.

[0441] It may be particularly advantageous to control the rate of dehydration. A higher than optimal rate of dehydration may, for example, lead to formation and / or spread of cracks, defects, or deformations in the biomass, whereas a lower than optimal rate may lead to further growth of mycelium in the biomass.

[0442] The sensor 40 may be configured to record a temperature of the biomass. Temperature may be recorded based, at least in part, on an image of the biomass obtained by an infrared camera, for example. Alternatively, or additionally, temperature may be measured by probes or resistance temperature detectors, or thermocouples, located in the biomass. Alternatively, or additionally, temperature may be measured by any other suitable method, including, but not limited to, contact or non-contact sensors.

[0443] As described above, the sensor 40 may be configured to record the sensor data at different times during the process. In particular, the sensor 40 may record the sensor data periodically, at pre-defined time intervals. The pre-defined intervals may be constant, or may vary over time. The system 1, particularly the data processing unit 10 thereof, may be configured to send data to the sensor 40 related, at least in part, to any of the pre-defined time intervals. The control of a rate at which the sensor data is recorded may be of advantage in enhancing an energy efficiency of the system 1. The system 1, particularly the data processing unit 10 thereof, may be configured to determine a characterization value for a characterization parameter of the biomass based, at least in part, on the sensor data. The determination of the value of the control parameter may be based, at least in part, on the characterization value so determined.

[0444] For example, the characterization parameter may comprise any of a strength (determined, for example, based on the density of the biomass), a heat-resistance, a fire-resistance capability, a noise insulation, or an appearance of the biomass and the corresponding characterization value may indicate the corresponding property of the biomass. In particular, some characterization values may represent a grade rather than a measured value of a physical property. For example, the characterization values for fire-resistance capability may comprise a grade ranging, for example, from very high to very low.

[0445] The characterization value may comprise a number, the number being associated with a measure of the characterization property. For example, the number may correspond to the value of the Young's modulus of the biomass, a higher number indicating greater strength. However, the number may alternatively be associated with a class / grade, such as 1, 2, ..., 10, a higher (or lower) number denoting greater strength, for example.

[0446] The system 1 may be of particular advantage in monitoring and / or controlling the growth of the biomass as described above. In particular, the data processing unit 10 may be configured to use a model to determine the value for the control parameter of the process. A model may generally be understood to accept an input and to produce an output based, at least in part, on the input.

[0447] The model may comprise a model based on heuristics. For example, the heuristic-based model may comprise a defined variation of the value for the control parameter over time and / or stage of growth of the biomass. The data processing unit 10 may, for example, be configured to determine the stage of growth based, at least in part, on the sensor data and to then determine the value for the control parameter.

[0448] The model may, alternatively, or additionally, comprise a model based on artificial intelligence. The artificial intelligence-based model may comprise a model based on any of supervised or unsupervised learning. The model may comprise, for example, a model based on any of a neural network (for example, multilayer perceptrons, a transformer, a convolutional neural network, or any other suitable model), a decision tree, or an SVM. In particular, the model may preferably comprise a model based on a neural network.

[0449] The model may comprise a trained model. The trained model may, for example, be retrieved from an external device by means of the communication unit 50 of the system 1. Alternatively, or additionally, the system 1, particularly the data processing unit 10 thereof, may be configured to generate the trained model by training a model. The generated model may be sent to the external device by means, for example, of the communication unit 50 of the system 1.

[0450] The model may be trained using supervised learning, wherein labeled data, comprising data associated with a label, may be sent as input to the model, the label indicating a desired output of the model. The desired output may be compared to an actual output of the model and one or more parameters of the model may be adjusted to decrease a discrepancy between the desired and actual outputs.

[0451] As described above, the output of the model may, in particular, be used, at least in part, to determine the value for the control parameter. Thus, the label associated with the data may relate, at least in part, to a desired value for the control parameter.

[0452] The input to the model may comprise, at least in part, the sensor data, or at least a part thereof, recorded by the sensor 40 as described above. The input to the model may comprise, at least in part, data related to the sensor data, such as the time associated with the sensor data as described above.

[0453] The system 1, particularly the data processing unit 10 thereof, may be configured to determine the characterization value for a characterization parameter, as described above, based, at least in part, on the sensor data, or the data related thereto, or at least a part thereof by means, at least in part, of the model. The system 1, particularly the data processing unit 10 thereof, may be configured to output the characterization value so determined. In other words, an output of the model may comprise, at least in part, the determined characterization value.

[0454] The system 1 may be configured to store the characterization value so determined and / or an association between the characterization value so determined and the sensor data, or the data related thereto, or the part thereof, based, at least in part, on which the characterization value is determined.

[0455] Training the model to determine the characterization value may comprise sending labeled data, wherein the label may relate, at least in part, to a desired characterization value. The desired characterization value may be based, for example, on a measured value. For example, the characterization parameter may comprise the Young's modulus of the biomass, and the characterization value may comprise the value of the Young's modulus measured. The labeled data may comprise sensor data, or data related thereto, recorded for the biomass at least significantly concurrently as the measurement of the Young's modulus. Alternatively, the characterization value may comprise a class / grade, as described above, based on the measured value. The measured value may comprise, further exemplarily, an apparent porosity or specific surface area of the biomass determined using a percentage of pixels in an image of the biomass with an intensity lower than a pre-defined threshold and the characterization value may be between 0 and 9 representing, for example, a percentage of pixels between 0 and 100%.

[0456] The input to the model may further comprise, at least in part, sensor data previously stored by the system 1. In particular, the sensor data previously stored may relate, at least in part, to a previous state of the biomass as described above. Thus, the model may be used to determine the value for the control parameter based, at least in part, also on a previous state of the biomass.

[0457] For example, the model may be configured for time-series analysis on the sensor data stored previously and recorded currently. Based on the corresponding time-series analysis, the model may determine the value for the control parameter.

[0458] Training the model to determine the value for the control parameter based, at least in part, on the sensor data stored previously and recorded currently may comprise, for example, sending labeled data as input to the model wherein the label may be related, at least in part, to a desired value for the control parameter, and wherein the data may comprise data at least similar to sensor data recorded previously.

[0459] For example, if the sensor data comprises images from a camera, the sensor data stored previously may comprise images stored previously corresponding, as described above, to previous states of the biomass. The labeled data may then comprise a series of images ordered in time (that may be sent as input to the model one at a time) and a label representing a desired value for the control parameter.

[0460] The input to the model may comprise, at least in part, a desired characterization value of a characterization parameter. For example, the input may comprise a grade of 10 in strength representing a highest level of strength. Further exemplarily, the input may comprise an image of a desired biomass.

[0461] The system 1, particularly the data processing unit 10 thereof, may be configured to determine the value for the control parameter based, at least in part, on the desired characterization value.

[0462] Training the model to determine the value for the control parameter based, at least in part, on a desired characterization value may comprise sending labeled data as input to the model wherein data may comprise data at least similar to a desired characterization value, and the label may be related, at least in part, to a value for the control parameter such that the input desired characterization value is, at least significantly, reached. The value for the control parameter may, additionally, or alternatively, be determined by the system 1, particularly the data processing component 10 thereof, to mitigate the formation and / or growth of any of a crack, a defect, a deformation, or contamination in the biomass. For example, the biomass may be used to manufacture a panel to be used in the construction industry as described above. It may, then, be advantageous to ensure that the biomass does not have a crack, a deformation, a defect, or any sign of contamination or other structural or visual defect. For example, an un-grown region may be considered such a defect. An un-grown region may be understood to comprise a region over which mycelium is determined to not have grown.

[0463] The system 1, particularly the data processing unit 10 thereof, may be configured to detect the presence of any structural or visual defects, such as a crack, a defect, a deformation, or contamination in the biomass by means, at least in part, of the model. For example, the input to the model may comprise an image recorded by the sensor 40 and the model may be configured to detect any of a crack, a defect, a deformation, or contamination in the image. Detection may comprise not only detecting presence but also determining a location and / or a size. The detection may be accomplished by any well-known image processing methods such as convolutional neural networks or edge detections, etc. and the model may be appropriately configured or trained therefor.

[0464] In response to having detected any of the crack, defect, deformation, or contamination in the image of the biomass, the value of the control parameter may be determined so as to mitigate formation and / or further growth of any of a crack, a defect, a deformation, or mold in the biomass. Thus, embodiments of the system 1 may allow improving a quality of products manufactured using biomass by improving a quality of the biomass produced.

[0465] The label, as described above, may be generated manually, or semi-automatically. In particular, the label may be generated, for example, based, at least in part, on commonly available knowledge of the process. The label may, alternatively, be generated based, at least in part, on a numerical simulation of the process, or of a simplification thereof.

[0466] The label may comprise a ternary label corresponding, for any control parameter, to a value increase, decrease, or no change. This may be of advantage in simplifying the model. Alternatively, the label may comprise a numerical value.

[0467] Thus, the system 1, particularly the data processing unit 10 thereof, may be configured for determining the value for the control parameter based, at least in part, on various input data as described above.

[0468] The control parameter may comprise any parameter relevant at any stage of the process. In particular, the control parameter may comprise any of a choice of one or more species of mycelium, a choice of a substrate, or at least a part thereof, a fraction of the substrate, or of its part, a choice and / or an amount of an additive such as a nutrient, or a starting moisture level in the initial stages of growth. In a later stage, the control parameter may comprise an environmental parameter affecting the growth process such as any of a humidity, a temperature, lighting conditions (e.g., brightness and / or hue), or a concentration of a substance (e.g., particulate matter / gas) in the growing environment. In the dehydration stage, the control parameter may comprise any of a humidity, or a temperature of the environment.

[0469] By allowing for storing associations between the determined value for the control parameter or the characterization value and the sensor data, or the data related thereto, based, at least in part, on which the (characterization) value is determined, the system 1 may thus allow learning which processes (defined, for example, by a sequence of values of the control parameter) lead to high-quality (defined, for example, by a less number of cracks, defects, deformations, or mold spots) biomass and which process lead to low-quality biomass.

[0470] For example, based on one set of sensor data, a value for the control parameter is determined, that may then be "understood" (by the model) to cause, at least in part, the next set of sensor data recorded. Further, all values of the control parameter determined prior to recording of a defined set of sensor data may be "understood" to cause (or result in), at least in part, the defined set of sensor data and, thus, the state of the biomass corresponding to the defined set of sensor data. Thus, the system 1, particularly the model of the data processing unit 10 thereof, may "learn" from the causal relationships defined by the associated sensor data and the determined values for the control parameter or the characterization values and allow determination of the value(s) of the control parameter resulting in optimal growth of biomass.

[0471] Overall, embodiments of the present technology may, thus, be of particular relevance for quality control of the process of growing the biomass as well as of manufacturing a final product based thereon.

[0472] Whenever a relative term, such as "about", "substantially" or "approximately" is used in this specification, such a term should also be construed to also include the exact term. That is, e.g., "substantially straight" should be construed to also include "(exactly) straight".

[0473] Whenever steps were recited in the above or also in the appended claims, it should be noted that the order in which the steps are recited in this text may be accidental. That is, unless otherwise specified or unless clear to the skilled person, the order in which steps are recited may be accidental. That is, when the present document states, e.g., that a method comprises steps (A) and (B), this does not necessarily mean that step (A) precedes step (B), but it is also possible that step (A) is performed (at least partly) simultaneously with step (B) or that step (B) precedes step (A). Furthermore, when a step (X) is said to precede another step (Z), this does not imply that there is no step between steps (X) and (Z). That is, step (X) preceding step (Z) encompasses the situation that step (X) is performed directly before step (Z), but also the situation that (X) is performed before one or more steps (Yl), followed by step (Z). Corresponding considerations apply when terms like "after" or "before" are used.

[0474] While in the above, preferred embodiments have been described with reference to the accompanying drawings, the skilled person will understand that these embodiments were provided for illustrative purpose only and should by no means be construed to limit the scope of the present invention, which is defined by the claims.

Claims

1. 54Claims1. A method for controlling a process of growing a biomass, wherein the method comprises: determining a value for a control parameter of the process, and wherein the process comprises mixing together a substrate and mycelium.

2. The method according to the preceding claim, wherein the method comprises sending the value for the control parameter to a control unit, wherein the control unit is configured to control an actuator, and wherein the method comprises activating and / or deactivating the actuator based, at least in part, on the value for the control parameter.

3. The method according to any of the preceding claims, wherein determining the value for the control parameter comprises using a model, and wherein the model comprises, at least in part, an artificial intelligence-based model.

4. The method according to any of the preceding claims, wherein the method comprises receiving data from a sensor, that may be referred to as sensor data, and / or wherein the method comprises receiving data related, at least in part, to the sensor data, and wherein the method comprises determining the value for the control parameter based, at least in part, on the sensor data, or the data related, at least in part, thereto.

5. The method according to the preceding claim, wherein the method comprises receiving data from a sensor, that may be referred to as sensor data, wherein the sensor data is related, at least in part, to a current state of the biomass.

6. The method according to any of the preceding claims, wherein determining the value for the control parameter is based, at least in part, on sensor data related, at least in part, to a previous state of the biomass.

7. The method according to any of the preceding claims and with the features of claim 4, wherein the sensor comprises a particle sensor, and wherein the sensor comprises a camera.

8. The method according to the preceding claim and with the features of claim 3, wherein the data received from the camera comprises an image, wherein the method comprises detecting, using, at least in part, the model, any of a crack, a defect, a deformation, or contamination in the image, and wherein the method comprises, in response to having detected any of a crack, a defect, a deformation, or contamination in the image, determining, using, at least in part, the model, a value for the control parameter to, at least, mitigate formation of any of a crack, a defect, a deformation, or contamination in the biomass.

559. The method according to any of the preceding claims, wherein the biomass is characterized by a characterization parameter, the characterization parameter having a characterization value.

10. The method according to the preceding claim and with the features of claim 3, wherein the method comprises providing a desired characterization value for the characterization parameter as input to the model, and wherein the method comprises determining the value for the control parameter based, at least in part, on the desired characterization value.

11. The method according to claim 3, wherein the method comprises storing an association between the determined value for the control parameter and the sensor data, or the data related, at least in part thereto, based, at least in part, on which the value for the control parameter is determined.

12. A system for controlling a process of growing a biomass, wherein the system is configured to: determine a value for a control parameter of the process, wherein the process comprises mixing together a substrate and mycelium.

13. The system according to the preceding claim, wherein the system comprises a data processing unit configured to determine the value for the control parameter.

14. A computer program product comprising instructions when run on a data processing unit of a system according to claim 13, to perform the method according to any of the claims 1 - 11.

15. A use of the system and / or the method according to any of the claims 1 - 13 respectively to control a process for growing a biomass, wherein the process comprises mixing together a substrate and mycelium.

Images