Digital twin sensing method, device and storage medium for edible mushroom production equipment

Abstract

This invention provides a digital twin sensing method for edible mushroom production equipment. The method collects multi-source data on environment, equipment operation, layer, and mushroom bag images to form a raw data stream. After time-series alignment, anomaly removal, missing value compensation, and standardization preprocessing, a corrected spatial mapping relationship is constructed based on spatial distance, occlusion, ventilation, and spraying correlations to calculate the local microenvironment parameters of each mushroom bag unit. Growth stages are divided by integrating mushroom bag image features, and a digital twin model is built and updated in real-time with the virtual-real mapping data. By constructing microenvironmental deviation indicators and equipment execution response consistency indicators in stages, environmental deviations are compared with equipment control effects. When control fails, optimized equipment parameters and anomaly warnings are output. This invention solves the shortcomings of traditional single-point sensing, which is difficult to characterize the local microenvironment of mushroom bags and cannot identify equipment idle operation. It improves the accuracy of microenvironmental measurement and equipment fault prediction capabilities, and is suitable for precise control in edible mushroom factory production.

Description

Technical Field

[0001] This invention relates to the field of agricultural equipment operation monitoring technology, and in particular to a digital twin sensing method, device, and storage medium for edible fungi production equipment. Background Technology

[0002] The industrialized production of edible fungi has high requirements for temperature, humidity, carbon dioxide concentration, light, ventilation and spraying conditions. These factors directly affect mycelial growth, primordium formation, fruiting body development and yield stability. As a result, the development of intelligent agricultural equipment has led to the widespread installation of temperature, humidity, carbon dioxide and light sensors, as well as fans, spraying systems, valve actuators and image acquisition devices in cultivation rooms for environmental monitoring and automatic adjustment.

[0003] However, existing edible mushroom production equipment still has limitations. On the one hand, sensor data is mostly point-based data, while the cultivation rack has a multi-layer, multi-column, and multi-regional structure. Problems such as uneven temperature and humidity, carbon dioxide retention, insufficient spray coverage, and light blockage can easily occur between different layers and mushroom bag units. A small amount of point-based data is difficult to accurately reflect the local microenvironment of the mushroom bag. On the other hand, current control methods mostly rely on fixed thresholds or single-parameter adjustments, lacking a comprehensive judgment of the mushroom bag growth stage, equipment execution status, and environmental response results. It is difficult to identify ineffective execution problems such as the fan starting but carbon dioxide not decreasing, or the spraying being executed but humidity not improving.

[0004] Digital twin technology can map the state of physical equipment to a virtual space, providing support for production status perception and fault early warning. However, if only sensor data is displayed without spatial modeling of sensor nodes, culture rack layers, and mushroom bag units, it is still difficult to meet the needs of local microenvironment reconstruction and equipment execution feedback verification. Therefore, it is necessary to propose a digital twin sensing method for the microenvironment of mushroom bags in edible mushroom production equipment that integrates multi-source sensor data, culture rack spatial structure, mushroom bag growth status, and equipment execution status. Summary of the Invention

[0005] To address the shortcomings of the existing technologies, this invention provides a digital twin sensing method, device, and storage medium for edible fungi production equipment, thereby solving the problems of point-based sensing data, difficulty in accurately reconstructing the local microenvironment of the mushroom bags, lack of consistency between equipment execution status and environmental improvement results, and untimely anomaly warnings in existing edible fungi production equipment.

[0006] To achieve the above objectives, the present invention provides a digital twin sensing method for edible fungi production equipment, comprising:

[0007] S1. Collect multi-source sensor data during the operation of edible fungi production equipment. The multi-source sensor data includes environmental parameters of the cultivation room, equipment execution parameters, cultivation rack layer information and mushroom bag image data, and form an original multi-source sensor data stream according to a unified sampling cycle.

[0008] S2. Perform time synchronization, outlier processing, missing value compensation and standardization on the original multi-source sensor data stream in sequence to obtain a standardized sensor data stream.

[0009] S3. Combining the spatial structure parameters of the culture chamber, sensor installation positions, culture rack layer information, ventilation path and spray coverage relationship, establish a corrected spatial mapping relationship between sensor nodes, culture rack layers and mushroom bag units, and calculate the local microenvironment state of each mushroom bag unit based on the standardized sensor data stream.

[0010] S4. By integrating the local microenvironment state, equipment execution state, and mushroom bag image features, a digital twin state model of edible mushroom production equipment is constructed. A unique mapping relationship is established between the physical mushroom bag unit, the physical culture rack layer, the physical equipment execution mechanism, and the corresponding digital twin object. The digital twin state model is dynamically updated according to a unified sampling period.

[0011] S5. Based on the updated digital twin state model, the microenvironmental deviation of the mushroom bag, the equipment execution intensity and the microenvironment improvement are correlated and calculated to obtain the equipment execution response consistency index. Based on the matching relationship between the microenvironmental deviation of the mushroom bag and the equipment execution response consistency index, the equipment control parameters and abnormal warning information are output.

[0012] In some embodiments, the multi-source sensor data in step S1 includes at least the culture chamber temperature, relative humidity, carbon dioxide concentration, light intensity, fan speed, spray pressure, valve opening, culture rack layer information, and mushroom bag image data; the original multi-source sensor data stream at the k-th sampling time is represented as:

[0013]

[0014] in, For the temperature of the incubation room, Relative humidity, This refers to the concentration of carbon dioxide. Light intensity, This refers to the fan speed. For spray pressure, For valve opening, For the identification of culture rack layers, This is image data of the mushroom bag.

[0015] In some embodiments, step S2, which sequentially performs time synchronization, outlier processing, missing value compensation, and standardization on the original multi-source sensor data stream, includes:

[0016] Sensor data with different sampling frequencies are unified onto the same time axis, and adjacent valid data are used to compensate for missing sampling points.

[0017] Data that significantly exceeds the sensor's measurement range or the sliding window's fluctuation range is marked as abnormal and replaced with valid data from the neighborhood.

[0018] Normalize or standardize sensor data of different dimensions to form a standardized sensor data stream under the same time series.

[0019] In some embodiments, the corrected spatial mapping relationship between the sensor nodes, culture rack layers, and culture bag units in step S3 is determined by the corrected spatial influence weight, which is expressed as:

[0020]

[0021] in, For the first The sensor node pairs with the first The correction space of each bacterial bag unit affects the weight. For the first The sensor node and the first Spatial distance between individual mushroom bag units This is the structural correction factor. For correction factor, The number of sensor nodes involved in the calculation; the structural correction coefficient is used to characterize the impact of rack obstruction, substrate density, ventilation path, or spray coverage on the environmental representativeness of the sensor nodes.

[0022] In some embodiments, the structural correction factor is determined by a combination of shielding strength, ventilation connectivity, and sprinkler coverage correlation, and its expression is:

[0023]

[0024] in, Indicates the first The sensor node and the first The spatial obstruction intensity between individual mushroom bag units, and The larger the value, the more severe the occlusion. This indicates the connectivity of the ventilation paths between the two. This indicates the correlation between the two in terms of spray coverage; , , These are the weighting coefficients.

[0025] In some embodiments, when there is a culture rack baffle, dense shading of the mushroom bags, or airflow obstruction between the sensor node and the mushroom bag unit, the environmental impact weight of the corresponding sensor node is reduced; when the two are in the same ventilation path or the same spray coverage area, the environmental impact weight of the corresponding sensor node is increased.

[0026] The modified spatial mapping relationship can also be determined using a distance decay function, a spatial interpolation function, or a graph structure adjacency weighting method.

[0027] In some embodiments, the image features of the mushroom bag in step S4 include: mycelial coverage, surface color features of the mushroom bag, outline features of the fruiting area, and cap morphology features. Based on the image features of the mushroom bag, a mushroom bag growth status identifier is generated. The digital twin state model of the edible fungi production equipment synchronously writes the local microenvironment state, equipment execution state, mushroom bag growth state, and historical state changes into the digital twin object of the corresponding mushroom bag unit.

[0028] In some embodiments, the expression for the microenvironment deviation index of the spawn bag in step S5 is:

[0029]

[0030] in, For the first The spawn unit in the first Micro-environmental deviation index at any given time , , , The first The local temperature, local humidity, local carbon dioxide concentration, and local light intensity of each incubator unit. , , , These are the target temperature, target humidity, target carbon dioxide concentration, and target light intensity for the current growth stage of the spawn bag. , , , These are the corresponding weighting coefficients, which are dynamically adjusted according to the growth status of the spawn bags.

[0031] In some embodiments, the equipment execution response consistency index in step S5 is expressed as:

[0032]

[0033] in, For the first The equipment in the area where each spawn unit is located performs consistent response indicators. For the first Time to the The amount of microenvironment improvement over time. The equipment execution intensity of fans, spray valves, ventilation valves, supplementary lighting equipment, or temperature control equipment within the same time period. This is a correction factor.

[0034] In some embodiments, when the microenvironmental deviation index of the mushroom bag exceeds a preset deviation threshold and the consistency index of equipment execution response is lower than a preset response threshold, it is determined that there is insufficient equipment execution response or local control abnormality in the area where the corresponding mushroom bag unit is located.

[0035] Another aspect of the present invention provides a digital twin sensing device for edible fungi production equipment, used to implement the digital twin sensing method for edible fungi production equipment as described above, the sensing device comprising:

[0036] The multi-source data acquisition module is used to collect multi-source sensor data during the operation of edible fungi production equipment and form a raw multi-source sensor data stream according to a unified sampling cycle.

[0037] The data preprocessing module is used to perform time synchronization, outlier handling, missing value compensation, and standardization on the raw multi-source sensor data stream to obtain a standardized sensor data stream.

[0038] The microenvironment reconstruction module is used to establish the corrected spatial mapping relationship between sensor nodes, culture rack layers and spawn bag units, and to calculate and reconstruct the local microenvironment state at each spawn bag unit level;

[0039] The digital twin modeling and updating module is used to construct a digital twin state model of edible fungi production equipment, establish a unique mapping relationship between entities and digital twin objects, and dynamically update the model.

[0040] The deviation assessment and early warning module is used to correlate and calculate the microenvironmental deviation index of the mushroom bag and the consistency index of equipment execution response, and generate equipment control parameters and abnormal early warning information.

[0041] In another aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the steps of the digital twin sensing method for edible fungi production equipment as described above are implemented.

[0042] Compared with the prior art, the present invention has the following advantages:

[0043] The digital twin sensing method for edible fungi production equipment provided by this invention relates to the fields of intelligent edible fungi production equipment, digital twins, multi-sensor fusion sensing and agricultural equipment operation monitoring. By collecting environmental parameters, equipment execution parameters, culture rack layer information and mushroom bag image data, the operating status of edible fungi production equipment, the state of the culture environment and the growth status of the mushroom bags are incorporated into a unified sensing process. The digital twin state model is dynamically updated to link the physical equipment, local microenvironment, growth stage and historical state changes, thereby improving the synchronicity and traceability of production process data.

[0044] The digital twin sensing method for edible fungi production equipment provided by this invention introduces structural correction coefficients and spatial influence weights to convert limited point sensing data into local microenvironmental states oriented towards the mushroom bag unit. This can more accurately reflect the differences in temperature, humidity, carbon dioxide concentration, and light intensity between different culture rack layers and different mushroom bag units, thereby improving the accuracy of local environmental perception.

[0045] The digital twin sensing method for edible fungi production equipment provided by this invention constructs microenvironmental deviation indicators for mushroom bags and consistency indicators for equipment execution response. It can comprehensively evaluate local environmental deviations based on the environmental requirements of different growth stages and identify abnormal situations where "equipment has been activated but the environment has not improved." This improves the ability to identify abnormal operation of fans, sprayers, valves, and supplementary lighting equipment, and provides support for precise control and stable operation of industrialized edible fungi production. Attached Figure Description

[0046] Figure 1 This is a schematic diagram of the overall process of the digital twin sensing method for edible fungi production equipment as shown in an embodiment of the present invention;

[0047] Figure 2 This is a diagram illustrating the architecture of a digital twin sensing device for edible fungi production equipment, as shown in an embodiment of the present invention.

[0048] Figure 3 This is a flowchart of the digital twin sensing method for edible fungi production equipment as shown in an embodiment of the present invention;

[0049] Figure 4 This is a schematic diagram illustrating the local microenvironment reconstruction of the bacterial bag and the equipment execution response judgment in an embodiment of the present invention;

[0050] In the attached figures, the following labels are used:

[0051] 300 - Digital twin sensing device for edible fungi production equipment;

[0052] 310 - Multi-source data acquisition module;

[0053] 320 - Data Preprocessing Module;

[0054] 330 - Microenvironment Reconstruction Module;

[0055] 340 - Digital Twin Modeling Update Module;

[0056] 350 - Deviation Assessment and Early Warning Module;

[0057] Steps: S1-S5. Detailed Implementation

[0058] See Figure 1 An embodiment of the present invention provides a digital twin sensing method for edible fungi production equipment, comprising:

[0059] S1. Collect multi-source sensor data during the operation of edible fungi production equipment. The multi-source sensor data includes environmental parameters of the cultivation room, equipment execution parameters, cultivation rack layer information and mushroom bag image data, and form an original multi-source sensor data stream according to a unified sampling cycle.

[0060] S2. Perform time synchronization, outlier processing, missing value compensation and standardization on the original multi-source sensor data stream in sequence to obtain a standardized sensor data stream.

[0061] S3. Combining the spatial structure parameters of the culture chamber, sensor installation positions, culture rack layer information, ventilation path and spray coverage relationship, establish a corrected spatial mapping relationship between sensor nodes, culture rack layers and mushroom bag units, and calculate the local microenvironment state of each mushroom bag unit based on the standardized sensor data stream.

[0062] S4. By integrating the local microenvironment state, equipment execution state, and mushroom bag image features, a digital twin state model of edible mushroom production equipment is constructed. A unique mapping relationship is established between the physical mushroom bag unit, the physical culture rack layer, the physical equipment execution mechanism, and the corresponding digital twin object. The digital twin state model is dynamically updated according to a unified sampling period.

[0063] S5. Based on the updated digital twin state model, the microenvironmental deviation of the mushroom bag, the equipment execution intensity and the microenvironment improvement are correlated and calculated to obtain the equipment execution response consistency index. Based on the matching relationship between the microenvironmental deviation of the mushroom bag and the equipment execution response consistency index, the equipment control parameters and abnormal warning information are output.

[0064] The digital twin sensing method for edible fungi production equipment provided by this invention does not directly use the sensor-collected values ​​as the overall environmental state of the cultivation chamber. Instead, it converts the point-sensing data into local microenvironmental data at the unit level of the mushroom bag by correcting the spatial influence weight. It does not only rely on fixed thresholds for alarms, but also calculates microenvironmental deviation indicators in combination with the growth stage of the mushroom bag. It does not only determine whether the equipment performs an action, but also determines whether the action brings about effective environmental improvement by using the consistency index of the equipment's execution response, thereby forming a digital twin sensing closed loop for edible fungi production equipment.

[0065] This invention first establishes a corrected spatial mapping relationship between sensor nodes, culture rack layers, and spawn bag units. Based on spatial distance, a structural correction coefficient is introduced to characterize the impact of spatial shading, spawn bag density, ventilation path, and spray coverage on the environmental representativeness of the sensor nodes. This structural correction coefficient can be determined by a combination of shading intensity, ventilation connectivity, and spray coverage correlation, allowing the environmental representativeness of the same sensor node for different spawn bag units to dynamically change according to the actual spatial structure. Through this processing, the system can convert a limited number of point-based sensor data into local temperature, local humidity, local carbon dioxide concentration, and local light intensity at the spawn bag unit level, thereby solving the problem of the difficulty in directly measuring the local environment in multi-layer culture racks.

[0066] Specifically, in this embodiment, the multi-source sensor data in step S1 includes at least the culture chamber temperature, relative humidity, carbon dioxide concentration, light intensity, fan speed, spray pressure, valve opening, culture rack layer information, and mushroom bag image data; the original multi-source sensor data stream at the k-th sampling time is represented as:

[0067]

[0068] in, For the temperature of the incubation room, Relative humidity, This refers to the concentration of carbon dioxide. Light intensity, This refers to the fan speed. For spray pressure, For valve opening, For the identification of culture rack layers, This is image data of the mushroom bag.

[0069] In this embodiment, step S2, which sequentially performs time synchronization, outlier processing, missing value compensation, and standardization on the original multi-source sensor data stream, includes:

[0070] Sensor data with different sampling frequencies are unified onto the same time axis, and adjacent valid data are used to compensate for missing sampling points.

[0071] Data that significantly exceeds the sensor's measurement range or the sliding window's fluctuation range is marked as abnormal and replaced with valid data from the neighborhood.

[0072] Normalize or standardize sensor data of different dimensions to form a standardized sensor data stream under the same time series.

[0073] In this embodiment, the corrected spatial mapping relationship between sensor nodes, culture rack layers, and culture bag units in step S3 is determined by the corrected spatial influence weight, which is expressed as follows:

[0074]

[0075] in, For the first The sensor node pairs with the first The correction space of each bacterial bag unit affects the weight. For the first The sensor node and the first Spatial distance between individual mushroom bag units This is the structural correction factor. For correction factor, The number of sensor nodes involved in the calculation; the structural correction coefficient is used to characterize the impact of rack obstruction, substrate density, ventilation path, or spray coverage on the environmental representativeness of the sensor nodes.

[0076] In this embodiment, the structural correction coefficient is determined by a combination of shielding strength, ventilation connectivity, and sprinkler coverage correlation, and its expression is:

[0077]

[0078] in, Indicates the first The sensor node and the first The spatial obstruction intensity between individual mushroom bag units, and The larger the value, the more severe the occlusion. Used to characterize the degree of unobstructedness or spatial accessibility; This indicates the connectivity of the ventilation paths between the two. This indicates the correlation between the two in terms of spray coverage; , , These are the weighting coefficients.

[0079] When there are culture rack baffles, dense shading of mushroom bags, or airflow obstruction between the sensor node and the mushroom bag unit, the environmental impact weight of the corresponding sensor node is reduced; when the two are in the same ventilation path or the same spray coverage area, the environmental impact weight of the corresponding sensor node is increased.

[0080] The modified spatial mapping relationship can also be determined using a distance decay function, a spatial interpolation function, or a graph structure adjacency weighting method.

[0081] In this embodiment, the image features of the mushroom bag in step S4 include: mycelial coverage, surface color features of the mushroom bag, outline features of the fruiting area, and cap morphology features. Based on the image features of the mushroom bag, a mushroom bag growth status identifier is generated. The digital twin state model of the edible fungi production equipment synchronously writes the local microenvironment state, equipment execution state, mushroom bag growth state, and historical state changes into the digital twin object of the corresponding mushroom bag unit.

[0082] This embodiment combines the target environmental parameters corresponding to the current growth stage of the spawn bag to construct a microenvironment deviation index for the spawn bag. This index can comprehensively reflect the degree of deviation of local temperature, local humidity, local carbon dioxide concentration, and local light intensity from the target growth conditions. Furthermore, it can dynamically adjust the weights of each parameter according to different stages such as mycelial culture, color change, primordia formation, fruiting, or harvesting, avoiding biased judgments caused by single fixed threshold alarms. The system can also determine the main sources of deviation based on the proportion of different environmental parameters in the overall deviation and generate corresponding ventilation, spraying, supplemental lighting, or temperature control adjustment parameters.

[0083] Specifically, the expression for the microenvironment deviation index of the spawn bag in step S5 is as follows:

[0084]

[0085] in, For the first The spawn unit in the first Micro-environmental deviation index at any given time , , , The first The local temperature, local humidity, local carbon dioxide concentration, and local light intensity of each incubator unit. , , , These are the target temperature, target humidity, target carbon dioxide concentration, and target light intensity for the current growth stage of the spawn bag. , , , These are the corresponding weighting coefficients, which are dynamically adjusted according to the growth status of the spawn bags.

[0086] This embodiment introduces an equipment execution response consistency index to determine whether the local microenvironment of the mushroom bag has been effectively improved after the fan, spray valve, ventilation valve, supplemental lighting equipment, or temperature control equipment performs its actions. When the microenvironment deviation in a certain area continuously exceeds the limit and the equipment execution response consistency index is lower than the preset response threshold, it indicates a mismatch between the equipment action and the environmental improvement. The system can then determine that there are abnormalities such as insufficient ventilation response, insufficient spray coverage, delayed temperature control response, supplemental lighting obstruction, or failure of local environmental control in the corresponding area. In this way, the present invention can identify hidden equipment execution abnormalities that are difficult to detect with traditional single-threshold alarms.

[0087] The equipment execution response consistency index in step S5 is expressed as follows:

[0088]

[0089] in, For the first The equipment in the area where each spawn unit is located performs consistent response indicators. For the first Time to the The amount of microenvironment improvement over time. The equipment execution intensity of fans, spray valves, ventilation valves, supplementary lighting equipment, or temperature control equipment within the same time period. This is a correction factor. This index is used to characterize the improvement effect of the local microenvironment brought about by the unit equipment execution intensity. When A larger value indicates a significant improvement in the local environment after the equipment is deployed; when... When the response is less than the preset response threshold, it indicates that the equipment's actions are not in line with the environmental improvement.

[0090] When the microenvironmental deviation index of the mushroom bag exceeds the preset deviation threshold and the consistency index of equipment execution response is lower than the preset response threshold, it is determined that there is insufficient equipment execution response or local control abnormality in the area where the corresponding mushroom bag unit is located.

[0091] See Figure 2 Another embodiment of the present invention provides a digital twin sensing device 300 for edible fungi production equipment, used to implement the digital twin sensing method for edible fungi production equipment as described in the above embodiments, the sensing device comprising:

[0092] The multi-source data acquisition module 310 is used to collect multi-source sensor data during the operation of edible fungi production equipment and form an original multi-source sensor data stream according to a unified sampling cycle.

[0093] Data preprocessing module 320 is used to perform time synchronization, outlier handling, missing value compensation and standardization on the raw multi-source sensor data stream to obtain a standardized sensor data stream;

[0094] The microenvironment reconstruction module 330 is used to establish the corrected spatial mapping relationship between sensor nodes, culture rack layers and microbial bag units, and to calculate and reconstruct the local microenvironment state of each microbial bag unit level.

[0095] The digital twin modeling and updating module 340 is used to construct a digital twin state model of edible fungi production equipment, establish a unique mapping relationship between entities and digital twin objects, and dynamically update the model.

[0096] The deviation assessment and early warning module 350 is used to correlate and calculate the microenvironmental deviation index of the mushroom bag and the consistency index of equipment execution response, and generate equipment control parameters and abnormal early warning information.

[0097] Another embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, it implements the steps of the digital twin sensing method for edible fungi production equipment as described in the above embodiments.

[0098] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below. Figure 3 This is a flowchart of the digital twin sensing method for edible fungi production equipment shown in the embodiment of the present invention, which is used to illustrate the overall process of multi-source sensor data acquisition, data preprocessing, local microenvironment reconstruction, digital twin model updating, response consistency judgment and anomaly warning output; Figure 4 This is a schematic diagram of the local microenvironment reconstruction of the spawn bag and the response judgment of the equipment execution shown in the embodiment of the present invention. It is used to illustrate the spatial mapping relationship between sensor nodes, culture rack layers and spawn bag units, as well as the environmental feedback judgment relationship after the execution of equipment such as fans, sprayers, and supplemental lighting.

[0099] like Figure 3 As shown in the embodiment of the present invention, the digital twin sensing method for the microenvironment of mushroom bags in edible fungi production equipment includes, in sequence, multi-source sensor data acquisition, data preprocessing, correction spatial mapping, reconstruction of the local microenvironment of the mushroom bag, dynamic updating of the digital twin state model, microenvironment deviation calculation, equipment execution response consistency judgment, and output of control parameters and abnormal warnings. Figure 3 The various processing steps constitute a complete process from physical production equipment to digital twin state model and then to anomaly feedback output.

[0100] like Figure 4 As shown, in this embodiment of the invention, environmental sensors, equipment operation sensors, and image acquisition devices are arranged in the multi-layer culture rack structure of the culture chamber. The sensor nodes and the culture bag units are established through spatial distance, culture rack obstruction, ventilation path, and spray coverage relationship to establish a corrected spatial mapping. Figure 4 The connection relationships between sensor nodes, culture rack layers, and culture bag units are used to represent the correction spatial influence weights; Figure 4The feedback from the fans, sprinklers, and supplemental lighting equipment is used to represent the closed-loop relationship between the changes in the local microenvironment after the equipment is executed and the judgment of the consistency of the response.

[0101] In this embodiment of the invention, the edible fungi production equipment includes a cultivation chamber, multi-layer cultivation racks, ventilation equipment, spraying equipment, supplemental lighting equipment, valve actuators, environmental sensor nodes, and a mushroom bag image acquisition device. Temperature and humidity sensors are deployed in different areas and layers of the cultivation chamber to collect temperature and relative humidity data; carbon dioxide sensors are deployed in ventilation dead zones, the central area of ​​the cultivation racks, or high-density mushroom bag areas to collect carbon dioxide concentration data; light sensors are used to collect light intensity data in the cultivation area; fan speed sensors are used to collect the operating status of the ventilation equipment; pressure sensors are used to collect the pressure of the spraying pipeline; valve opening sensors are used to collect the opening degree of the spray valves or ventilation valves; and the image acquisition device is used to acquire images of the mushroom bag surface.

[0102] The system follows a uniform sampling period Collect multi-source data, and in the first Constructing the original sensing data vector at each sampling time:

[0103]

[0104] For sensor data acquired at different frequencies, the system first aligns them to a unified time axis; for short-term missing data, it compensates with adjacent valid data; for data exceeding the sensor's range or the fluctuation range of the sliding window, it marks them as outliers and replaces them with neighboring valid values; for data of different dimensions, it performs normalization or standardization processing. After the above processing, a standardized sensor data stream is obtained, which serves as the input for spatial mapping and digital twin modeling.

[0105] During the spatial mapping correction process, the system reads the spatial structure parameters of the culture chamber, the height of the culture rack, the sensor installation coordinates, and the coordinates of the culture bag unit, and calculates the first... The sensor node and the first Spatial distance between individual spawn bags Simultaneously, the system determines the structural correction coefficient based on factors such as the shielding of the culture rack, the density of the spawn bags, the ventilation path, and the spray coverage. And calculate the weight of the correction space influence:

[0106]

[0107] The structural correction factor can be determined by a combination of shielding strength, ventilation connectivity, and sprinkler coverage correlation:

[0108]

[0109] When the sensor node and the spawn bag unit are in the same ventilation path or the same spray coverage area, the higher value is taken for ventilation connectivity or spray coverage correlation; when there are cultivation rack baffles, dense spawn bag obstruction, or airflow blockage between them, the higher value is taken for obstruction strength. This reduces the weight of the corresponding sensor node's environmental influence on the mushroom bag unit. Therefore, the system can avoid errors caused by reconstructing the local environment solely based on straight-line distance and improve the accuracy of calculating the local microenvironment state at the mushroom bag unit level. Without departing from the technical concept of this invention, the corrected spatial mapping relationship can also be implemented using a distance attenuation function, a spatial interpolation function, or a graph structure adjacency weighting method.

[0110] Based on the aforementioned corrected spatial influence weights, the system calculates the first... Local temperature of each spawn unit Local humidity Local carbon dioxide concentration and local light intensity The aforementioned local microenvironment data is written into the digital twin object of the corresponding bacterial bag unit to characterize the local state of the physical culture environment in virtual space.

[0111] In terms of image processing of the mushroom bag, the image acquisition device acquires images of the mushroom bag surface according to a preset cycle. The system performs grayscale correction, noise filtering, edge enhancement, and target region segmentation on the mushroom bag images, extracting mycelial coverage, surface color features, fruiting area contour features, and cap morphological features. Based on the above image features, the system determines the growth stage of the mushroom bag, which may include mycelial cultivation period, color change period, primordium formation period, fruiting period, and harvesting period, and writes the mushroom bag growth status identifier into the corresponding digital twin object.

[0112] During the digital twin modeling process, the system constructs virtual objects in virtual space corresponding to the culture chamber, culture rack, spawn bag unit, ventilation equipment, spraying equipment, supplemental lighting equipment, valve actuators, and sensor nodes, based on the structural parameters of the culture chamber, the layout parameters of the culture rack, the equipment installation positions, and the sensor node positions. Each spawn bag unit corresponds to a digital twin object, and a mapping relationship is established between the physical spawn bag unit, the physical culture rack layer, the physical equipment actuator, and the digital twin object. The digital twin object records the local microenvironment state, the spawn bag growth state, the equipment execution state, and historical state changes. After the physical sensor data is updated, the system synchronously updates the corresponding digital twin object according to a unified sampling period and retains the difference between the before and after states for calculating the microenvironment improvement and the consistency index of equipment execution response.

[0113] Edible fungi have different environmental parameter requirements at different growth stages. The system retrieves the target environmental parameters for the corresponding growth stage based on the growth status identifier of the fungal bag. Let's say the first... The target temperature, target humidity, target carbon dioxide concentration, and target light intensity for the current growth stage of each spawn unit are as follows: , , , The microenvironment deviation index of the spawn bag is defined as follows:

[0114]

[0115] in, , , , These are weighting coefficients for temperature, humidity, carbon dioxide concentration, and light intensity, respectively. Each weighting coefficient can be dynamically set according to the importance of different edible fungi varieties and different growth stages. For example, during the mycelial culture stage, temperature and humidity have a significant impact on mycelial expansion, so the corresponding weights for temperature and humidity are increased; during the fruiting stage, humidity, carbon dioxide concentration, and light intensity have a significant impact on primordia formation and fruiting body development, so the corresponding weights for humidity, carbon dioxide concentration, and light intensity are increased.

[0116] The system can also determine the main sources of deviation based on the proportion of each environmental parameter in the overall deviation. When the carbon dioxide concentration deviation accounts for the highest proportion, the system prioritizes generating parameters for adjusting fan speed or ventilation frequency; when the humidity deviation accounts for the highest proportion, the system prioritizes generating parameters for adjusting spray pressure, spray cycle, or humidification; when the temperature deviation accounts for the highest proportion, the system prioritizes generating parameters for adjusting ventilation, heating, or cooling; and when the light deviation accounts for the highest proportion, the system prioritizes generating parameters for adjusting supplementary lighting intensity or duration.

[0117] During the equipment's response consistency judgment process, the system first calculates the... The spawn unit in the first Time to the Microenvironmental improvement over time And calculate the equipment execution intensity of fans, spray valves, ventilation valves, supplementary lighting equipment or temperature control equipment within the same time period. Based on this, the equipment execution response consistency index is expressed as:

[0118] when When this occurs, it indicates that the microenvironmental deviation has decreased, and the environment tends to improve after equipment adjustment; when If the deviation in the microenvironment does not decrease or continues to increase, it indicates that the equipment's performance is insufficient. The larger the value, the more significant the improvement in the local environment brought about by the unit equipment's execution intensity; when When the response value is less than the preset response threshold, it indicates a mismatch between the equipment action and the environmental response. When the microenvironmental deviation index of the mushroom bag exceeds the preset deviation threshold and the consistency index of the equipment execution response is lower than the preset response threshold, the system determines that there is insufficient equipment execution response or local control abnormality in the area where the corresponding mushroom bag unit is located.

[0119] The system's final output of anomaly warning information includes the time of anomaly occurrence, the area of ​​anomaly, the shelf level of the culture rack, the unit number of the culture bag, the type of anomaly, microenvironmental deviation indicators, equipment execution response consistency indicators, and suggested control measures. This information is also written to a historical database for subsequent production traceability, batch analysis, and equipment maintenance.

[0120] Specific Implementation Example 1: Identification of Insufficient Ventilation Response.

[0121] In this embodiment, a five-layer cultivation rack is set up in the edible fungus cultivation chamber, with several spawn bags arranged on each layer. Temperature and humidity sensors and carbon dioxide sensors are deployed in the upper, middle, and lower parts of the cultivation chamber, as well as near the ventilation inlet and outlet. A speed sensor is deployed at the fan, and a valve opening sensor is deployed at the ventilation valve. The system calculates and corrects the spatial influence weights based on the spatial distance between the sensor nodes and the spawn bags, the occlusion relationship of the cultivation racks, and the ventilation path, and reconstructs the local carbon dioxide concentration of each spawn bag unit. During the fruiting stage, the target carbon dioxide concentration range for the lower spawn bags on the fifth layer can be set to 800–1200 ppm. The system detected that the carbon dioxide concentration in this area rose to 1800 ppm, and the carbon dioxide deviation was the main deviation item. Subsequently, the fan speed was increased from 900 r / min to 1300 r / min, but the local carbon dioxide concentration remained above 1600 ppm for 10 consecutive minutes, the microenvironmental deviation did not decrease significantly, and the equipment execution response consistency index was lower than the preset response threshold. Based on this, the system determines that there is insufficient ventilation response or local carbon dioxide retention in the area, outputs an early warning of "insufficient ventilation response of the lower culture rack", and generates maintenance suggestions to increase the air exchange frequency, check for air duct blockage, and verify the operating status of the fan.

[0122] Specific Implementation Example 2: Identification of Insufficient Spray Coverage.

[0123] In another embodiment, the system deploys pressure sensors on the main spray pipeline and branch spray pipelines, valve opening sensors at the spray valves, and humidity sensors at different levels of the cultivation rack. The system calculates the local humidity of each spawn bag unit by adjusting the spatial influence weights and calls the target humidity based on the current growth status of the spawn bags. During the fruiting stage, the target humidity range for the spawn bag unit in the middle of the third layer can be set to 88%–95%. The system detects that the local humidity in this area has dropped to 78%, and the humidity deviation is the main deviation item. Therefore, it generates control parameters to increase the spray pressure and extend the spray duration. After the spray pressure is increased from 0.20 MPa to 0.32 MPa, the local humidity remains below 82% for 8 consecutive minutes, indicating a small improvement in the microenvironment and the equipment execution response consistency index is below the preset response threshold. The system determines that there is insufficient spray coverage, nozzle blockage, or local humidity compensation failure in this area, outputs a "insufficient spray coverage in the middle layer cultivation rack" warning, and generates maintenance suggestions to check nozzle blockage, branch pipeline pressure, and spray valve response status.

[0124] Specific Implementation Example 3: Identification of Lighting Obstruction and Insufficient Local Illumination.

[0125] In this embodiment, for edible fungi production scenarios requiring light induction or supplemental lighting management, supplemental lighting equipment and light sensors are installed in the cultivation room. The light sensors are respectively deployed in the upper, middle, and lower layers of the cultivation rack. Since the structure of the cultivation rack, the density of the spawn bags, and the installation position of the equipment may cause light obstruction, the system introduces a structural correction coefficient when calculating the spatial influence weight. When there is obstruction between the sensor node and the spawn bag unit by the cultivation rack or dense obstruction by spawn bags, the influence of the corresponding sensor node on the light reconstruction of that spawn bag unit is reduced. During the primordia formation period, the target light intensity of the spawn bag unit in the inner obstruction area of ​​the second layer can be set to 300–500 lx. The system detects that the local light intensity is consistently below 180 lx, and the light deviation accounts for the main deviation item. Therefore, it generates control parameters to increase the supplemental lighting intensity or extend the supplemental lighting duration. If the light intensity in the area still does not reach the target range after the output intensity of the supplementary lighting equipment is increased, and the consistency index of the equipment execution response is lower than the preset response threshold, the system determines that there is supplementary lighting obstruction, lamp attenuation, or uneven local light distribution in the area, outputs a warning of "insufficient local supplementary lighting response", and generates maintenance suggestions for adjusting the lamp angle, checking lamp attenuation, and optimizing the supplementary lighting arrangement in the area obstructed by the culture rack.

[0126] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the disclosure herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not disclosed herein. The specification and embodiments are to be considered exemplary only.

[0127] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A digital twin sensing method for edible fungi production equipment, characterized in that: include: S1. Collect multi-source sensor data during the operation of edible fungi production equipment. The multi-source sensor data includes environmental parameters of the cultivation room, equipment execution parameters, cultivation rack layer information and mushroom bag image data, and form an original multi-source sensor data stream according to a unified sampling cycle. S2. Perform time synchronization, outlier processing, missing value compensation and standardization on the original multi-source sensor data stream in sequence to obtain a standardized sensor data stream. S3. Combining the spatial structure parameters of the culture chamber, sensor installation positions, culture rack layer information, ventilation path and spray coverage relationship, establish a corrected spatial mapping relationship between sensor nodes, culture rack layers and mushroom bag units, and calculate the local microenvironment state of each mushroom bag unit based on the standardized sensor data stream. S4. By integrating the local microenvironment state, equipment execution state, and mushroom bag image features, a digital twin state model of edible mushroom production equipment is constructed. A unique mapping relationship is established between the physical mushroom bag unit, the physical culture rack layer, the physical equipment execution mechanism, and the corresponding digital twin object. The digital twin state model is dynamically updated according to a unified sampling period. S5. Based on the updated digital twin state model, the microenvironmental deviation of the mushroom bag, the equipment execution intensity and the microenvironment improvement are correlated and calculated to obtain the equipment execution response consistency index. Based on the matching relationship between the microenvironmental deviation of the mushroom bag and the equipment execution response consistency index, the equipment control parameters and abnormal warning information are output.

2. The digital twin sensing method for edible fungi production equipment according to claim 1, characterized in that: The multi-source sensor data in step S1 includes at least the culture chamber temperature, relative humidity, carbon dioxide concentration, light intensity, fan speed, spray pressure, valve opening, culture rack layer information, and mushroom bag image data; the original multi-source sensor data stream at the k-th sampling time is represented as: in, For the temperature of the incubation room, Relative humidity, This refers to the concentration of carbon dioxide. Light intensity, This refers to the fan speed. For spray pressure, For valve opening, For the identification of culture rack layers, This is image data of the mushroom bag.

3. The digital twin sensing method for edible fungi production equipment according to claim 1, characterized in that: The process of performing time synchronization, outlier processing, missing value compensation, and standardization on the original multi-source sensor data stream in step S2 includes: Sensor data with different sampling frequencies are unified onto the same time axis, and adjacent valid data are used to compensate for missing sampling points. Data that significantly exceeds the sensor's measurement range or the sliding window's fluctuation range is marked as abnormal and replaced with valid data from the neighborhood. Normalize or standardize sensor data of different dimensions to form a standardized sensor data stream under the same time series.

4. The digital twin sensing method for edible fungi production equipment according to claim 1, characterized in that: In step S3, the corrected spatial mapping relationship between sensor nodes, culture rack layers, and culture bag units is determined by the corrected spatial influence weight, which is expressed as follows: in, For the first The sensor node pairs with the first The correction space of each bacterial bag unit affects the weight. For the first The sensor node and the first Spatial distance between individual mushroom bag units This is the structural correction factor. For correction factor, The number of sensor nodes involved in the calculation; the structural correction coefficient is used to characterize the impact of rack obstruction, substrate bag density, ventilation path, or spray coverage on the environmental representativeness of the sensor nodes.

5. The digital twin sensing method for edible fungi production equipment according to claim 4, characterized in that: The structural correction factor is determined by a combination of shielding strength, ventilation connectivity, and sprinkler coverage correlation, and its expression is: in, Indicates the first The sensor node and the first The spatial obstruction intensity between individual mushroom bag units, and The larger the value, the more severe the occlusion. This indicates the connectivity of the ventilation paths between the two. This indicates the correlation between the two in terms of spray coverage; , , These are the weighting coefficients.

6. The digital twin sensing method for edible fungi production equipment according to claim 5, characterized in that: When there are culture rack baffles, dense shading of mushroom bags, or airflow obstruction between the sensor node and the mushroom bag unit, the environmental impact weight of the corresponding sensor node is reduced; when the two are in the same ventilation path or the same spray coverage area, the environmental impact weight of the corresponding sensor node is increased. The modified spatial mapping relationship can also be determined using a distance decay function, a spatial interpolation function, or a graph structure adjacency weighting method.

7. The digital twin sensing method for edible fungi production equipment according to claim 1, characterized in that: The image features of the mushroom bag in step S4 include: mycelial coverage, surface color features of the mushroom bag, outline features of the fruiting area, and cap morphology features. Based on the image features of the mushroom bag, a mushroom bag growth status identifier is generated. The digital twin state model of the edible fungi production equipment synchronously writes the local microenvironment state, equipment execution state, mushroom bag growth state, and historical state changes into the digital twin object of the corresponding mushroom bag unit.

8. The digital twin sensing method for edible fungi production equipment according to claim 1, characterized in that: The expression for the microenvironmental deviation index of the spawn bag in step S5 is as follows: in, For the first The first spawn unit in the... Micro-environmental deviation index at any given time , , , The first The local temperature, local humidity, local carbon dioxide concentration, and local light intensity of each incubator unit. , , , These are the target temperature, target humidity, target carbon dioxide concentration, and target light intensity for the current growth stage of the spawn bag. , , , These are the corresponding weighting coefficients, which are dynamically adjusted according to the growth status of the spawn bags.

9. The digital twin sensing method for edible fungi production equipment according to claim 1, characterized in that: The equipment execution response consistency index in step S5 is expressed as follows: in, For the first The equipment in the area where each spawn unit is located performs consistent response indicators. For the first Time to the The amount of microenvironment improvement over time. The equipment execution intensity of fans, spray valves, ventilation valves, supplementary lighting equipment, or temperature control equipment within the same time period. This is a correction factor.

10. The digital twin sensing method for edible fungi production equipment according to claim 9, characterized in that: When the microenvironmental deviation index of the mushroom bag exceeds the preset deviation threshold and the consistency index of equipment execution response is lower than the preset response threshold, it is determined that there is insufficient equipment execution response or local control abnormality in the area where the corresponding mushroom bag unit is located.

11. A digital twin sensing device for edible fungi production equipment, characterized in that: For implementing the digital twin sensing method for edible fungi production equipment as described in any one of claims 1-10, the sensing device comprises: The multi-source data acquisition module is used to collect multi-source sensor data during the operation of edible fungi production equipment and form a raw multi-source sensor data stream according to a unified sampling cycle. The data preprocessing module is used to perform time synchronization, outlier handling, missing value compensation, and standardization on the raw multi-source sensor data stream to obtain a standardized sensor data stream. The microenvironment reconstruction module is used to establish the corrected spatial mapping relationship between sensor nodes, culture rack layers and spawn bag units, and to calculate and reconstruct the local microenvironment state at each spawn bag unit level; The digital twin modeling and updating module is used to construct a digital twin state model of edible fungi production equipment, establish a unique mapping relationship between entities and digital twin objects, and dynamically update the model. The deviation assessment and early warning module is used to correlate and calculate the microenvironmental deviation index of the mushroom bag and the consistency index of equipment execution response, and generate equipment control parameters and abnormal early warning information.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the digital twin sensing method for edible fungi production equipment as described in any one of claims 1-11.

Images