Parameter control method of preserved meat smoking process and smoking system

Abstract

The invention discloses a parameter control method of a preserved meat smoking process and a smoking system, which are applied to a control unit in the smoking system, the smoking system further comprises a humidifier, and the control unit is connected with the humidifier; the method comprises the following steps: collecting environmental parameters in a smoking system in a preserved meat smoking process; if the humidity value is smaller than a preset humidity threshold value, calculating a hardened layer growth rate of the surface layer of the preserved meat based on the obtained surface layer thickness value, calculating a salt penetration rate of the preserved meat based on the obtained salt penetration depth of the preserved meat, and judging whether the preserved meat has a surface layer hardening risk or not based on the hardened layer growth rate and the salt penetration rate; if yes, inputting the hardening layer growth rate and the salt permeation rate into a pre-constructed query table to map to obtain a humidity recommendation value of the current smoking process; the humidifier is controlled to adjust the ambient humidity within the body to the recommended humidity value. Therefore, according to the invention, the parameters of the preserved meat smoking process can be accurately controlled.

Description

Technical Field

[0001] This invention relates to the field of parameter control, and in particular to a parameter control method and smoking system for a cured meat smoking process. Background Technology

[0002] The smoking process of cured pork is essentially a complex and dynamic process involving the exchange of heat and mass between the internal moisture and salt content of the meat and the external environment. During this process, fluctuations in environmental parameters present multivariate, time-varying, and nonlinear control challenges. The core issue lies in maintaining a dynamic balance between the rate of internal dehydration and the rate of surface hardening in the cured pork. Specifically, while lower humidity promotes surface moisture evaporation for shaping, improper control can lead to excessively rapid dehydration, forming a dense, hardened shell. This shell severely hinders the outward expulsion of internal moisture and the inward penetration of salt. Once this balance is disrupted, it directly results in quality defects such as "dry outside, wet inside" and uneven saltiness in the cured pork. Therefore, achieving precise control of the smoking process parameters is not simply about stabilizing the environment, but rather about adaptively adjusting based on changes in the state of the cured pork to manage this complex process and ensure the final product's texture and flavor.

[0003] The commonly used quality control methods for smoked products are as follows: A hyperspectral detection method for color and texture changes during the smoking process of cured meat (patent number CN106525875A) includes: using a hyperspectral imaging system to scan and obtain three-dimensional data information blocks of cured meat at different smoking processing stages; calculating the average spectrum of the region of interest (ROI) of the cured meat sample and screening characteristic wavelengths; establishing a partial least squares regression prediction model for the color and texture of smoked cured meat based on the characteristic reflectance spectrum and image texture features of the sample; and drawing a color and texture distribution map of cured meat at different processing stages during the smoking process by predicting the color L*, a*, b* values ​​and texture indices (hardness, viscoelasticity) corresponding to each pixel in the spectral image, thereby realizing intelligent monitoring of the quality of smoked cured meat during the processing process and precise control of meat product quality and safety.

[0004] A meat product safety monitoring system based on big data (patent number CN119379109B) relates to the field of meat product production monitoring technology. This system monitors water activity, microbial content, oxidation level, and stain area at various production stages to promptly identify potential safety hazards and take corresponding measures, significantly reducing the risk of corrosion and spoilage. Through in-depth analysis of the difference dataset, the system can identify key links affecting meat product quality, thereby optimizing production processes and reducing unnecessary steps. Furthermore, when the system detects that the comprehensive diffusion index Ksz exceeds the risk threshold R, it can quickly generate early warning information and initiate control strategies to adjust production conditions in a timely manner to reduce the impact of corrosion diffusion on the product. By creating and sorting priority lists, the system enables managers to quickly identify the highest-risk monitoring sub-areas, thus concentrating resources and attention on the most critical intervention points.

[0005] However, the aforementioned technologies have the following technical problems: they mainly focus on monitoring and early warning of the quality of finished meat products or processes, and do not constitute a closed-loop control of the parameters of the bacon smoking process. In actual production, the commonly used control methods are still simple control methods based on fixed procedures or operator experience, such as adjusting the temperature and humidity of the smoking system in stages according to a preset time curve. These methods have two major drawbacks: first, at the perception level, they lack perception of the internal state of the bacon (such as the depth of salt penetration and the rate of hardening layer growth), and cannot capture the dynamic changes of the bacon itself, resulting in a lag in control actions; second, at the decision-making level, they cannot quantify, identify, and predict the risk of surface hardening, and therefore cannot adjust the temperature and humidity setpoints in a timely and accurate manner in feedforward or feedback control to proactively avoid hardening risks, resulting in seriously insufficient control accuracy. Summary of the Invention

[0006] This invention provides a parameter control method and smoking system for the smoking process of cured meat, which can achieve precise control of the parameters of the smoking process of cured meat, thereby ensuring the quality of cured meat.

[0007] An embodiment of the present invention provides a parameter control method and a smoking system for a cured meat smoking process. The control unit of the smoking system includes a body, a cured meat rack, an air inlet, an air outlet, a humidity sensor, a camera assembly, an infrared spectroscopy assembly, and a humidifier for increasing the humidity inside the body. The control unit is connected to the humidifier, the humidity sensor, and the camera assembly respectively. The parameter control method includes: The humidity sensor collects the humidity value within the smoking system during the smoking process of cured meat. If the humidity value is less than a preset humidity threshold, the hardening layer growth rate of the cured meat surface is calculated based on the surface thickness value of the cured meat on the cured meat placement rack obtained by the camera component, and the salt penetration rate of the cured meat is calculated based on the salt penetration depth of the cured meat obtained by the infrared spectroscopy component. Based on the hardening layer growth rate and the salt penetration rate, it is determined whether there is a risk of surface hardening of the cured meat. If so, the hardening layer growth rate and the salt penetration rate are input into a pre-built lookup table to map and obtain the recommended humidity value for the current smoking process. The lookup table is constructed based on the historical optimal process data of the cured meat smoking process. The humidifier is controlled to adjust the ambient humidity within the body to the recommended humidity value.

[0008] This invention, by monitoring the external environment while simultaneously monitoring the core internal and surface states of the cured meat itself, breaks through the limitations of traditional control methods that rely solely on environmental parameters. This provides indispensable multi-dimensional data support for accurately assessing the dynamic equilibrium of the smoking process, ensuring the comprehensiveness and scientific nature of control decisions from the outset. By dynamically converting state parameters into corresponding rates of change, it achieves a quantitative characterization of the complex smoking process, while also intuitively and dynamically revealing the trends and intensity of the smoking process, providing crucial feature inputs for risk warning and intelligent decision-making. By determining the existence of risks, it can identify risks before the dense, hardened shell actually forms and causes irreversible damage to the quality of the cured meat, gaining time for subsequent proactive intervention. The lookup table is based on... The construction of historical optimal process data ensures that the output target value is essentially a reuse of parameters from successful processes that have been verified in practice. This avoids unreliable outputs that may arise from complex models, guaranteeing the stability and reliability of the control effect. By comprehensively considering the dynamic changes in cured meat, the system ensures that the set humidity target value is highly matched with the actual processing requirements of the cured meat, thus achieving precise control. By directly and automatically applying the calculated optimal target value to the execution equipment, a complete closed-loop control system is formed. This completely changes the traditional extensive management that relies on manual experience, achieving precise control of the parameters of the cured meat smoking process. Ultimately, this ensures that the smoking quality of each batch of cured meat is uniform and stable, and effectively avoids quality defects such as localized rot and external dryness with internal dampness. Compared with existing technologies, this invention can achieve precise control of the parameters of the cured meat smoking process, thereby guaranteeing the quality of the cured meat.

[0009] Further, the calculation of the salt penetration rate of the cured meat based on the salt penetration depth obtained from the infrared spectroscopy component includes: The salt penetration depth of the cured meat is obtained through the infrared spectroscopy component, and the difference in salt penetration depth between adjacent sampling times is calculated based on the salt penetration depth. Based on the difference in salinity penetration depth, the initial salinity penetration rate is calculated respectively; The initial salt penetration rate was subjected to a moving average process to obtain the salt penetration rate inside the cured meat.

[0010] By dynamically converting state parameters into corresponding rates of change, a quantitative characterization of the complex smoking process is achieved. At the same time, the trend and intensity of the smoking process can be revealed intuitively and dynamically, providing key feature inputs for risk warning and intelligent decision-making.

[0011] Further, the calculation of the hardening layer growth rate of the cured meat surface based on the surface thickness value of the cured meat on the cured meat placement rack obtained by the camera component includes: The surface thickness value of the cured meat on the cured meat placement rack is obtained through the camera component; Identify outliers in the surface thickness value and remove them from the surface thickness value to obtain the processing result; The surface hardness difference between adjacent sampling times is calculated based on the processing results; Based on the surface hardness difference and the sampling time interval, the initial hardened layer growth rate is calculated. The initial hardened layer growth rate is smoothed and filtered to obtain the hardened layer growth rate.

[0012] By dynamically converting state parameters into corresponding rates of change, a quantitative characterization of the complex smoking process is achieved. At the same time, the trend and intensity of the smoking process can be revealed intuitively and dynamically, providing key feature inputs for risk warning and intelligent decision-making.

[0013] Furthermore, the determination of whether cured meat has a risk of surface hardening based on the hardening layer growth rate and the salt penetration rate includes: Calculate the time delay between the hardened layer growth rate and the salt penetration rate; Based on the time delay value, the time difference between the formation of the hardened layer and the penetration of salt to the same depth is determined within several consecutive smoking periods. The time difference fluctuation amplitude sequence is calculated based on each of the aforementioned time difference values; Based on the time difference fluctuation amplitude sequence, the cumulative increment value of hardened layer thickness and the cumulative increment value of salt penetration depth are determined; The total cumulative difference between the cumulative increment of the hardened layer thickness and the cumulative increment of the salt penetration depth from the start of smoking to the current smoking time is determined, and the risk of surface hardening of the cured meat is judged based on the total cumulative difference.

[0014] By assessing whether risks exist, these risks can be identified before the dense, hardened shell actually forms and causes irreversible damage to the quality of the cured meat, thus gaining time for subsequent proactive intervention.

[0015] Furthermore, the hardened layer growth rate and the salt penetration rate are input into a pre-built lookup table to map to a recommended humidity value for the current smoking process, including: The hardened layer growth rate and the salt permeation rate are mapped to corresponding discrete intervals to obtain the hardened layer growth rate interval and the salt permeation rate interval, respectively. Based on the combination of the hardened layer growth rate range and the salt penetration rate range, an index lookup is performed in the lookup table to obtain the recommended humidity value. The lookup table is determined by a mapping relationship formed by associating the historically optimal smoking process parameters with the corresponding historical recommended humidity values.

[0016] By comprehensively considering multi-dimensional information on the dynamic changes in cured meat, this ensures that the set humidity target value is highly matched with the actual processing needs of the cured meat, thereby achieving precise control.

[0017] Further, controlling the humidifier to adjust the humidity within the unit to the recommended humidity value includes: The recommended humidity value is converted into a corresponding humidity control signal, and the humidity control signal is sent to the humidifier corresponding to the main body via the industrial control bus; The humidifier adjusts its operating status according to the corresponding humidity control signal until the monitored target environmental parameters reach the recommended humidity value.

[0018] By converting the recommended humidity value into a corresponding control signal and then controlling it, precise control of the parameters of the bacon smoking process is achieved, fundamentally ensuring the uniformity and stability of the bacon quality.

[0019] Furthermore, the smoking system also includes a dehumidifier, and after determining whether there is a risk of surface hardening of the cured meat, it further includes: If there is no risk of surface hardening of the cured meat, then determine whether the humidity value is greater than the preset upper limit threshold humidity. If it is greater than the specified humidity value, a recommended dehumidification value is determined based on the humidity value and the preset upper limit threshold humidity. The dehumidifier is controlled to adjust the ambient humidity inside the body to the recommended dehumidification value.

[0020] By adjusting the ambient humidity of the smoking system when there is no hardened surface layer, the quality of cured meat can be improved.

[0021] Secondly, this application also provides a smoking system, including a main body, a control unit, a cured meat rack, an air inlet, an air outlet, a humidity sensor, a camera assembly, an infrared spectroscopy assembly, a humidifier, an exhaust fan, and a control unit; the humidity sensor, the camera assembly, the infrared spectroscopy assembly, the humidifier, and the exhaust fan are respectively signal-connected to the control unit; the control unit is used to implement the parameter control method for the cured meat smoking process as described in this application.

[0022] Furthermore, the smoking system also includes: the cured meat racks are spaced apart inside the main body; the air inlet is located on the lower part of one side wall of the main body; the air outlet is located on the upper part of the other side wall of the main body, forming an air circulation channel inside the main body; the humidifier is located on the side wall of the main body above the cured meat racks, and the dehumidifier is located on the inner wall of the main body.

[0023] Furthermore, the humidity sensor is used to collect the humidity value inside the body; the camera component is used to obtain the surface thickness value of the cured meat on the cured meat placement rack; and the infrared spectroscopy component is used to obtain the salt penetration depth of the cured meat. Attached Figure Description

[0024] To more clearly illustrate the technical solution of this application, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0025] Figure 1 This is a schematic diagram of the structure of one embodiment of the fumigation system provided in this application; Figure 2 This is a schematic flowchart of an embodiment of the parameter control method for the bacon smoking process provided in this application; Figure 3 This is a flowchart illustrating one embodiment of steps S301 to S305 provided in this application; Figure 4 This is a schematic flowchart of another embodiment of the parameter control method for the bacon smoking process provided in this application; Figure 5 This is a schematic diagram of another embodiment of the smoking system provided in this application. Detailed Implementation

[0026] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0027] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the application; the terms “comprising” and “having”, and any variations thereof, in the specification, claims, and foregoing description of the drawings are intended to cover non-exclusive inclusion.

[0028] In the description of the embodiments of this application, technical terms such as "first" and "second" are used only to distinguish different objects and should not be construed as indicating or implying relative importance or implicitly specifying the number, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly defined.

[0029] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0030] In the description of the embodiments in this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0031] In the description of the embodiments of this application, the term "multiple" refers to two or more (including two), similarly, "multiple sets" refers to two or more (including two sets), and "multiple pieces" refers to two or more (including two pieces).

[0032] In the description of the embodiments of this application, unless otherwise expressly specified and limited, technical terms such as "installation," "connection," "joining," and "fixing" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. For those skilled in the art, the specific meaning of the above terms in the embodiments of this application can be understood according to the specific circumstances.

[0033] During the smoking process of cured pork, fluctuations in ambient temperature and humidity present multivariate and time-varying nonlinear control challenges. While excessively low humidity is beneficial for the shaping of the meat surface, it can easily lead to the formation of a dense, hardened crust, hindering the expulsion of internal moisture and the penetration of salt, disrupting the internal and external dynamic balance, and causing uneven smoking. Existing technologies mostly rely on fixed procedures or experience-based control, lacking awareness of the cured pork's condition (such as the thickness of the hardened layer, moisture content, and salt penetration depth), and cannot quantify the risk of surface hardening. Consequently, it is difficult to achieve adaptive and precise control, hindering the stable improvement of smoking quality.

[0034] Figure 1 This is a schematic diagram of an embodiment of a smoking system provided in this application, applied to a control unit in the smoking system. The smoking system includes a main body 01, an air outlet 02, a cured meat rack 03, an air inlet 04, a humidity sensor (not shown in the figure), a camera assembly (not shown in the figure), an infrared spectroscopy assembly (not shown in the figure), and a humidifier (not shown in the figure) for increasing the humidity inside the main body. The humidifier is located on the side wall of the main body above the cured meat rack. The control unit is connected to the humidifier, the humidity sensor, and the camera assembly. The smoking system is a relatively enclosed environment. The roof is not shown in the figure to show the cured meat rack.

[0035] It should be noted that the production process of cured pork is generally as follows: First, fresh pork is obtained as the initial raw material; then, the pork is cleaned, impurities are removed, and it is cut into pork pieces suitable for processing; then, the pork pieces are placed in a vacuum tumbling device, and salt or other seasonings are evenly coated on the pork pieces for marinating; the marinated pork pieces are then placed in the smoking system of this application to complete the smoking process, so as to give the cured pork its unique flavor and color; finally, the smoked cured pork is cooled, trimmed, and packaged to obtain the finished cured pork.

[0036] It's important to note that during the smoking process, when humidity decreases, the outer shell of cured meat tends to harden. This hardening hinders internal substance exchange, affecting the quality of the cured meat. Conversely, excessive humidity prevents effective evaporation of surface moisture, leading to several problems: first, a stable, hardened outer shell is difficult to form, resulting in loose meat; second, mold and spoilage microorganisms easily grow, causing deterioration; and third, the color darkens, the smoky flavor doesn't penetrate sufficiently, and the overall quality declines. Therefore, precise control of the smoking process parameters is crucial to prevent excessively high or low humidity, thus improving the quality of the cured meat.

[0037] See Figure 2 To achieve precise control of parameters in the smoking process of cured pork, an embodiment of the present invention provides a parameter control method for the smoking process of cured pork, applicable to... Figure 1 The fumigation system includes steps S201 to S203: Step S201: The humidity value in the smoking system during the smoking process of cured meat is collected by the humidity sensor, and the surface thickness value of the cured meat on the cured meat placement rack is obtained by the camera component. In some embodiments, the humidity sensor collects the humidity value within the smoking system during the smoking process of cured meat. Specifically, the humidity sensor is first embedded in the inner wall of the main body at a mid-height position near the cured meat rack. This allows for direct monitoring of the most representative ambient humidity around the cured meat, while avoiding potential local airflow interference or measurement deviations caused by proximity to air inlets, outlets, or walls. Then, during the smoking process, the humidity sensor continuously collects the relative humidity value of the air in the factory at a preset sampling frequency (e.g., once per hour) and converts it into an electrical signal, which is then transmitted to the control unit. The control unit then performs analog-to-digital conversion and calibration on the received signal to obtain an accurate humidity value.

[0038] It should be noted that the cured meat rack can be directly fixed inside the smoking system, or it can be formed by hanging cured meat on the rack to create a cured meat cart, and then pushing the cart into the smoking system. This application does not impose any restrictions.

[0039] Step S102: If the humidity value is less than a preset humidity threshold, the growth rate of the hardened layer on the surface of the cured meat is calculated based on the surface thickness value, the salt penetration rate of the cured meat is calculated based on the salt penetration depth of the cured meat obtained by the infrared spectroscopy component, and the risk of surface hardening of the cured meat is determined based on the growth rate of the hardened layer and the salt penetration rate. If there is a risk, the growth rate of the hardened layer and the salt penetration rate are input into a pre-built lookup table to map the recommended humidity value for the current smoking process. The lookup table is constructed based on the historical optimal process data of the cured meat smoking process. In some embodiments, if the humidity value is less than a preset humidity threshold, specifically: after obtaining the humidity value, it is necessary to compare the humidity value with a preset humidity threshold (such as 65%), wherein the preset humidity threshold is a fixed value or configurable parameter pre-stored in the control unit; if the humidity value is less than the preset humidity threshold, it indicates that the ambient humidity has decreased, and there is a possibility that the cured meat is at risk of hardening. At this time, it is necessary to further analyze the cured meat to accurately determine whether there is a risk of surface hardening.

[0040] In some embodiments, calculating the hardening layer growth rate of the cured meat surface based on the surface thickness value of the cured meat on the cured meat rack acquired by the camera component includes: acquiring the surface thickness value of the cured meat on the cured meat rack through the camera component; identifying outliers in the surface thickness value and removing the outliers from the surface thickness value to obtain a processing result; calculating the surface hardness difference between adjacent sampling times based on the processing result; calculating the initial hardening layer growth rate based on the surface hardness difference and the sampling time interval; and performing smoothing filtering on the initial hardening layer growth rate to obtain the hardening layer growth rate. Specifically, firstly, when it is determined that the humidity value is less than a preset humidity threshold, the control unit controls the camera component (e.g., an industrial camera with high-definition microscopy or autofocus function) to acquire the surface thickness value of the cured meat on the cured meat rack; then, the acquired surface thickness value is subjected to data quality verification, and outliers are identified and removed. Then, the arithmetic mean of the effective thickness values ​​at adjacent times is typically used to replace the identified outliers or to remove the outliers to obtain a processing result. Subsequently, after obtaining the processing results, the surface thickness value at the next time moment is subtracted from the surface thickness value at the previous time moment to obtain the surface thickness state difference between adjacent sampling times. The surface thickness state difference is then divided by the time interval between adjacent sampling points to calculate the initial hardening layer growth rate. Finally, given that the hardening process of the cured meat surface is a relatively slow and continuous process, and the directly calculated initial hardening layer growth rate may be unstable due to small measurement fluctuations, a moving average method is needed to smooth and filter the initial hardening layer growth rate to filter out short-term noise interference and retain the low-frequency signal that can reflect the true trend of change, thereby obtaining a stable and reliable hardening layer growth rate.

[0041] In some embodiments, the surface thickness value of the cured meat on the cured meat rack obtained by the camera component is specifically as follows: First, the camera component is fixed to the top of the main body by a bracket and directly facing the placement area of ​​the cured meat rack. The installation height and focal length configuration must ensure that the texture and shape changes of the cured meat surface caused by hardening can be clearly distinguished. Then, the camera component is controlled to collect image data of the cured meat surface at a preset cycle (e.g., every ten minutes) during the smoking process (e.g., the cured meat rack includes three rows of racks, each row of racks can hold 10 cured meat samples, and the image data captured at this time is an image containing 10 cured meat samples), and the image data is transmitted to the control unit for analysis by the image processing algorithm built into the control unit. First, three typical cured meat samples are randomly extracted from the image data, with the cured meat regions being of consistent size during extraction. Then, the cured meat regions are preprocessed (e.g., noise reduction and contrast enhancement) and the edge contours are accurately identified. Next, the physical shrinkage of the surface layer due to drying and hardening is quantified by analyzing changes in surface texture roughness and local gloss differences within the contour area, or by using edge detection operators to locate the deformation boundary between the surface and inner layers. Finally, the estimated surface thickness, expressed in length units, is calculated by calibrating the relationship between image pixel size and actual physical size. The algorithm (e.g., the YOLO algorithm) can be trained and calibrated using known cured meat sample images and measured thickness data to achieve accurate measurement.

[0042] It should be noted that since the environment of each row of cured meats is similar, if there is a hardened layer, the corresponding surface thickness value will also be similar. Therefore, by processing typical cured meat samples (such as 3 samples) and averaging them, the thickness processing result is approximately the surface thickness value of the entire row of cured meats. In this way, we can know the surface thickness value of the entire row of cured meats, thereby improving the efficiency of subsequent processing.

[0043] It should be noted that the process of identifying outliers is as follows: the surface thickness values ​​arranged in chronological order of collection time are compared with the values ​​of the previous and next time moments. If the surface thickness value at a certain moment deviates from the average value of the values ​​of the previous and next time moments by more than a preset outlier threshold (e.g., 0.5 mm), then the surface thickness value at that moment is marked as outlier.

[0044] It should be noted that the rate of increase in the thickness of the hardened layer reflects the dynamic process of dehydration and hardening of the cured meat surface. When the ambient humidity decreases, the moisture on the surface of the cured meat evaporates rapidly, causing protein denaturation and aggregation, forming a hardened layer. By calculating the change in the thickness of the hardened layer per unit time, the speed of this hardening process can be quantitatively characterized.

[0045] In some embodiments, calculating the salt penetration rate of cured meat based on the salt penetration depth obtained by the infrared spectroscopy component includes: obtaining the salt penetration depth of the cured meat through the infrared spectroscopy component, and calculating the difference in salt penetration depth between adjacent sampling times based on the salt penetration depth; calculating the initial salt penetration rate based on the difference in salt penetration depth; and performing a moving average processing on the initial salt penetration rate to obtain the salt penetration rate inside the cured meat. Specifically, firstly, when the humidity value is less than a preset humidity threshold, the control unit controls the infrared spectroscopy component (such as a portable or online near-infrared spectrometer) to obtain the salt penetration depth; then, after obtaining the salt penetration depth, the rate is calculated using the difference method, that is, calculating the difference in salt penetration depth between two adjacent sampling times (this difference is usually negative, and the absolute value is used for calculation), and then dividing the difference in salt penetration depth by the sampling time interval to obtain the initial salt penetration rate, which characterizes the speed at which salt penetrates inward. Subsequently, since measurements may be affected by occasional faults or instantaneous environmental disturbances during the actual fumigation process, causing abnormal fluctuations in the initial rate value (such as negative values ​​or sudden increases), it is necessary to use the moving average method to filter out short-term noise interference from the initial salt permeation rate, retain the low-frequency signal that can reflect the true trend of change, and thus obtain a stable and reliable salt permeation rate.

[0046] In some embodiments, the salt penetration depth of the cured meat on the cured meat rack is obtained using the infrared spectroscopy component. Specifically, the infrared spectroscopy component is first installed at the same horizontal height as the cured meat rack, ensuring that the detection probe of the infrared spectroscopy component faces the cured meat on the rack. Then, during measurement, the infrared spectroscopy component emits near-infrared light of a specific wavelength onto the surface of the cured meat and receives its reflectance spectral data (for example, the cured meat rack includes three rows of shelves, each row of which can hold 10 cured meat samples; in this case, the reflectance spectrum contains the spectral data of 10 cured meat samples). Since sodium chloride, water, fat, and other components in the cured meat have characteristic absorption peaks in the near-infrared region, there is a quantitative relationship between the absorbance of its reflectance spectrum and the content of these components. Then, when the control unit acquires the reflectance spectral data, it randomly selects three typical spectral data using a screening tool and calls a pre-established quantitative analysis model calibrated with experimental data to analyze the typical spectral data, thereby non-destructively calculating the internal salt penetration depth of the cured meat at the current moment. The method for establishing the quantitative analysis model includes: collecting spectral data from a series of cured meat samples with known different salt penetration depths (obtained through destructive sampling and chemical analysis calibration); extracting spectral features using chemometric methods (such as partial least squares regression, PLS) and fitting them with the calibrated penetration depth values ​​to establish a prediction model; this model can then be used to non-destructively predict the salt penetration depth of the real-time acquired spectra.

[0047] It should be noted that the infrared spectroscopy component is installed on the side of the cured meat rack. The distance between its detection probe and the surface of the cured meat is adjusted according to the equipment specifications (usually within a non-contact effective range of several centimeters to tens of centimeters) and the size of the cured meat to ensure effective acquisition of spectral signals.

[0048] It should be noted that since the environment of each row of cured meat is similar, their salt penetration depth will also be relatively similar. Therefore, by processing the typical spectral data (such as 3) corresponding to typical cured meat samples and averaging them, the obtained salt penetration depth is approximately the salt penetration depth of the entire row of cured meat. In this way, the salt penetration depth of the entire row of cured meat can be known, thereby improving the efficiency of subsequent processing.

[0049] It should be noted that the salt penetration rate characterizes the speed at which salt penetrates from the surface of the cured meat into the interior. This rate is affected by the barrier effect of the hardened layer. When the hardened layer appears, the salt has difficulty penetrating further in, resulting in uneven smoking.

[0050] By dynamically converting state parameters into corresponding rates of change, a quantitative characterization of the complex smoking process is achieved. At the same time, the trend and intensity of the smoking process can be revealed intuitively and dynamically, providing key feature inputs for risk warning and intelligent decision-making.

[0051] Please refer to Figure 3 In some embodiments, determining whether cured meat has a risk of surface hardening based on the hardened layer growth rate and the salt penetration rate includes steps S301 to S305: Step S301: Calculate the time delay between the hardened layer growth rate and the salt penetration rate; In some embodiments, a cross-correlation function algorithm is used, with the salinity rate sequence as the moving sequence and the hardening layer growth rate sequence as the reference sequence. Starting from zero offset, the time offset is gradually increased (each offset is one sampling time interval). The sum of the products of the corresponding time values ​​of the two sequences after the offset is calculated, and then divided by the product of the sequence length and the standard deviation to obtain the normalized correlation coefficient. When the correlation coefficient reaches its peak, it indicates that the two sequences have reached the maximum similarity at that offset. The offset time at this point is the time delay between the formation of the hardening layer and the salt infiltration.

[0052] It should be noted that the time delay value reflects how long it takes for salt to penetrate to the corresponding depth after the hardened layer on the surface of the cured meat has formed. A positive value indicates that the hardening occurs first and the salt penetration is delayed. It is an important quantitative indicator for assessing whether the smoking process is coordinated.

[0053] Step S302: Based on the time delay value, determine the time difference between the formation of the hardened layer and the penetration of salt to the same depth within several consecutive smoking periods. In some embodiments, a first cumulative curve of the hardened layer thickness changing over time is obtained by integrating the hardened layer growth rate sequence over time; similarly, a second cumulative curve of the salt penetration depth is obtained by integrating the salt penetration rate sequence. Then, a specific depth reference point (e.g., 2 mm) is set, and the time T1 when the hardened layer thickness reaches that depth and the time T2 when the salt penetration depth reaches that depth are found on the first and second cumulative curves, respectively. The difference between these two times (T1 - T2) is the time difference value at that depth location at a specific time. A positive time difference value indicates that the hardened layer formation precedes salt penetration, while a negative time difference value indicates that salt penetration precedes hardened layer formation.

[0054] It should be noted that in the early stages of the actual smoking process, when the ambient humidity is high, the surface moisture of the cured meat evaporates slowly, and the hardening layer forms at a slower rate. At this time, salt can penetrate relatively quickly, and the time difference value may be negative or close to zero. As smoking progresses and the humidity gradually decreases, the hardening layer forms and thickens rapidly, beginning to hinder salt penetration, and the time difference value turns positive and gradually increases. When the humidity drops below 40%, the hardening layer becomes excessively dense, severely hindering salt penetration, and the time difference value increases sharply, indicating a serious imbalance in the coordination between the two processes.

[0055] Step S303: Calculate the time difference fluctuation amplitude sequence based on each of the time difference values; In some embodiments, firstly, the entire smoking process is divided into several consecutive smoking periods at fixed time intervals (e.g., every 4 hours). Then, for each period, the arithmetic mean of all time differences is calculated, followed by the squared deviation of each time difference from the arithmetic mean. The sum of these deviations is divided by the number of data points in that period, and the square root is taken to obtain the standard deviation. This standard deviation represents the fluctuation amplitude for that period, quantifying the stability of the synchronicity between the hardening layer formation and salt penetration processes within that period. Finally, the fluctuation amplitude values ​​for each period are arranged in chronological order to obtain the time difference fluctuation amplitude sequence.

[0056] In some embodiments, the relevant formula for calculating the fluctuation amplitude is: ; ; In the formula, This is the arithmetic mean of all time differences within the k-th time period; This represents the number of data points representing time differences sampled during the k-th time period. Let be the time difference value corresponding to the i-th sampling point in the k-th time period. Its physical meaning is the time difference between the formation of the hardened layer and the salt penetration reaching the same depth at a certain measurement moment. It represents the standard deviation of the time difference values ​​within the k-th time period, i.e., the fluctuation range of that time period.

[0057] It should be noted that the greater the fluctuation range, the less stable the coordination between the formation of the hardened layer and salt penetration during that period, and the worse the uniformity of the smoking process.

[0058] It should be noted that by analyzing the changes in the amplitude of fluctuations between adjacent time periods in the time difference fluctuation sequence (e.g., continuous increase or decrease), it is possible to determine whether the coordination of the smoking process is deteriorating or improving. If the amplitude of fluctuations continues to increase, it indicates that the incoordination between the formation of the hardened layer and salt infiltration is intensifying, requiring timely adjustment of environmental parameters. If the amplitude of fluctuations gradually decreases and tends to stabilize, it indicates that the two processes are becoming more coordinated, and the smoking process has entered a benign state.

[0059] Step S304: Based on the time difference fluctuation amplitude sequence, determine the cumulative increment value of the hardened layer thickness and the cumulative increment value of the salt penetration depth; In some embodiments, firstly, based on the aforementioned divided smoking periods, the hardened layer thickness growth rate value within each period is integrated over time to obtain the cumulative increment value of the hardened layer thickness, wherein the calculation formula is: ,in, This represents the cumulative increment in the hardened layer thickness during that period. For the first time period The hardened layer growth rate at each sampling time. The sampling time interval is defined as follows. Subsequently, using a similar method, the salinity rate values ​​within each time interval are integrated and accumulated to obtain the cumulative increment of salinity permeability depth for that time interval. The calculation formula is: ,in, This represents the cumulative increment of salt penetration depth during the i-th time period. Let be the salinity rate at the j-th sampling time within this period.

[0060] It should be noted that the cumulative increase in hardened layer thickness reflects the overall increase in the thickness of the hardened layer during that period, while the cumulative increase in salt penetration depth represents the total increase in the depth of salt penetration into the meat during that period.

[0061] Step S305: Determine the total cumulative difference between the cumulative increment of the hardened layer thickness and the cumulative increment of the salt penetration depth from the start of smoking to the current smoking time, and determine whether the cured meat has a risk of surface hardening based on the total cumulative difference.

[0062] In some embodiments, firstly, when the cumulative increment value of the hardened layer thickness is obtained... The cumulative increment value of the salinity penetration depth Next, the cumulative difference for each time period is calculated, using the following formula: Then, starting from the start of the smoking process, the cumulative difference value for each time period (from time period 1 to the current time period i) is calculated. By continuously summing the results, the total cumulative difference value is obtained. The relevant calculation formula is as follows: Finally, the total cumulative difference value The surface hardening risk is then determined by comparing it with a preset densification threshold.

[0063] It should be noted that the physical meaning of the single-time difference lies in quantifying the degree of imbalance between the growth of the hardened layer and salt penetration. When the cumulative increase in hardened layer thickness is greater than the cumulative increase in salt penetration depth, the difference is positive, indicating that the growth rate of the hardened layer exceeds the rate of salt penetration, and the hardened layer is forming a barrier. As the smoking process progresses, this imbalance gradually accumulates. By continuously summing the differences at each time period, the cumulative difference value can reflect the cumulative degree of the hardened layer's barrier effect throughout the entire smoking process.

[0064] It should be noted that the densification threshold is set based on historical data statistics of the cured meat smoking process (e.g., 3.0 mm). Under normal smoking conditions, the cumulative difference between the hardened layer thickness and the salt penetration depth should be maintained within the range of 2-3 mm. Exceeding this range indicates that the hardened layer has begun to over-densify. The high-risk threshold is set at 1.5 times the densification threshold. When the cumulative difference reaches 4.5 mm or more, it indicates that the hardened layer has severely hindered salt penetration, and the smoking quality faces serious risks. This application does not impose any restrictions on this.

[0065] It should be noted that the risk of surface hardening is a specific technical concept defined in this application to describe the inventive point. During the smoking process of cured meat, due to factors such as low environmental humidity, the dehydration and hardening rate of the surface of the cured meat is significantly faster than the penetration rate of internal salt, thus forming a hardened layer. This hardened layer will hinder the evaporation of internal moisture and the continued penetration of salt, ultimately causing the possibility or tendency for quality defects such as "dry outside and wet inside, uneven saltiness" in the cured meat. The hardened layer can be identified and quantified in the image as the area on the surface of the cured meat where its optical properties have changed significantly due to dehydration shrinkage and protein denaturation.

[0066] By assessing whether there is a risk of surface hardening in cured meat, the risk can be identified before the hardened layer actually forms and causes irreversible damage to the quality of the cured meat, thus gaining time for subsequent proactive intervention.

[0067] In some embodiments, when the total cumulative gap value exceeds the densification threshold (e.g., 3.0 mm), it is determined that there is a risk of surface hardening in the cured meat. At this point, it is necessary to determine how to adjust the treatment to avoid surface hardening of the cured meat in the future.

[0068] In some embodiments, the hardening layer growth rate and the salt penetration rate are input into a pre-constructed lookup table to map the recommended humidity value for the current smoking process. This includes: mapping the hardening layer growth rate and the salt penetration rate to corresponding discrete intervals to obtain hardening layer growth rate intervals and salt penetration rate intervals; and performing an index lookup in the lookup table based on the combination of the hardening layer growth rate intervals and the salt penetration rate intervals to obtain the recommended humidity value. The lookup table is determined based on a mapping relationship formed by associating historically optimal smoking process parameters with corresponding historical recommended humidity values. Specifically, firstly, the obtained hardening layer growth rate and salt penetration rate are mapped to predefined discrete intervals. For example, the hardening layer growth rate can be divided into three intervals: "low speed [0, 5)", "medium speed [5, 10)", and "high speed [10, ∞)"; the salt penetration rate can be divided into three intervals: "slow speed [0, 0.2)", "medium speed [0.2, 0.4)", and "fast speed [0.4, ∞)". Then, the "hardening layer growth rate range" and "salt penetration rate range" into which the rate value falls are combined as a composite index key to search in a pre-built lookup table to quickly and accurately retrieve the recommended humidity value that best matches the current process state. This lookup table is essentially a two-dimensional matrix, with its row index corresponding to the hardening layer growth rate range and its column index corresponding to the salt penetration rate range. Each cell stores a recommended humidity value that has been historically verified as optimal (e.g., target humidity 65%RH).

[0069] It should be noted that the construction of the query table is an offline process based on historical big data analysis and optimization, and is the core of ensuring the effectiveness of the entire control method. The construction process includes: First, collecting a large amount of historical optimal process data, which comes from past successful batches of cured meat smoking. Each data record includes the hardening layer growth rate, salt penetration rate monitored within a specific time period of that batch, and the historical recommended humidity value that was actually adopted and proven to be the best in that time period. Next, the collected continuous rate data is cleaned and interval discretized. The interval division rules (such as the numerical ranges of "low speed" and "medium speed" mentioned above) must be completely consistent with the rules used in the aforementioned matching stage. Then, the processed historical data is correlated and mapped. For all historical data points falling within the same combination of "hardening layer growth rate interval" and "salt penetration rate interval", cluster analysis (such as taking the mode) or optimization algorithms (such as taking the average of those data corresponding to the best quality of the finished cured meat) are used to determine the unique and optimal recommended humidity value under that interval combination, and this value is filled into the corresponding position in the query table. Ultimately, this results in a complete and stable lookup table that encapsulates historical best process experience, enabling the system to achieve the optimal control strategy through simple index lookup when running online.

[0070] By comprehensively considering the dynamic changes in the cured meat, this ensures that the set humidity target value is highly matched with the actual processing needs of the cured meat, thereby achieving precise control.

[0071] In some embodiments, the smoking system further includes a dehumidifier. After determining whether the cured meat has a risk of surface hardening, the system further includes: if the cured meat does not have a risk of surface hardening, determining whether the humidity value is greater than a preset humidity upper limit threshold; if it is greater, determining a recommended dehumidification value based on the humidity value and the preset humidity upper limit threshold; and controlling the dehumidifier to adjust the ambient humidity inside the body to the recommended dehumidification value. Specifically, firstly, if it is determined that the cured meat does not have surface hardening chromatography after judging by the hardening layer growth rate and the salt penetration rate, it is necessary to determine whether the humidity value is greater than a preset humidity upper limit threshold (e.g., 75%). If the current humidity value is greater than this preset humidity upper limit threshold, the control unit determines a recommended dehumidification value based on the humidity value and the preset humidity upper limit threshold. Then, after determining the recommended dehumidification value, the control unit generates a corresponding control command and sends it to the dehumidifier via the industrial control bus. Subsequently, the dehumidifier starts and adjusts its dehumidification power according to the command, actively discharging the humid air inside the smoking system through the air outlet until the ambient humidity inside the body, as monitored by the humidity sensor, decreases and stabilizes at the recommended dehumidification value.

[0072] It should be noted that the recommended dehumidification value can be determined by: calculating the difference between the current humidity value and the preset humidity upper limit threshold, and then, based on the magnitude of the difference, mapping a specific target humidity value (i.e., the recommended dehumidification value) through a preset proportional-integral algorithm or a dehumidification lookup table. This value is usually equal to or slightly lower than the preset humidity upper limit threshold to ensure effective dehumidification and avoid frequent start-ups and shutdowns of the equipment.

[0073] It should be noted that this preset humidity upper limit threshold is different from the preset humidity threshold used to trigger humidification and risk assessment. It defines the upper limit of humidity allowed in the smoking process. When the humidity is higher than the preset humidity upper limit threshold (e.g., 75%), the system considers the environment to be too humid, which may lead to other quality problems even if there is no risk of surface hardening. On the other hand, the preset humidity threshold is the lower limit. When the humidity is lower than the preset humidity threshold (e.g., 65%), the system considers the environment to be too dry, which may cause the surface of the cured meat to harden.

[0074] This process complements humidification control, together maintaining the humidity of the smoke environment precisely within the optimal process range defined by preset humidity thresholds and preset upper humidity thresholds.

[0075] In some embodiments, determining the recommended humidity value for the current smoking process based on the hardening layer growth rate and the salt penetration rate may further include: normalizing the hardening layer growth rate and the salt penetration rate to form an input vector; inputting the input vector into a pre-trained deep learning model, wherein the deep learning model is a long short-term memory network; extracting temporal features from the input vector through the long short-term memory network to output a feature representation vector characterizing the current smoking state; and inputting the feature representation vector into the fully connected layer at the end of the long short-term memory network to obtain the recommended humidity value through calculation mapping. Specifically, firstly, the control unit normalizes the calculated hardening layer growth rate V_h and salt penetration rate V_s to eliminate the influence of dimensions, scaling them to the interval [0,1] to form a two-dimensional input vector [V_h_norm, V_s_norm] for the current moment. Subsequently, to capture the dynamic temporal patterns of process parameters, the system combines the normalized vectors of the current moment and multiple consecutive sampling moments prior to it (e.g., the sequence data of the past 30 minutes) into a temporal matrix as input. This temporal matrix is ​​then fed into a pre-trained Long Short-Term Memory (LSTM) network model. Leveraging its internal gating mechanisms (including input, forget, and output gates), the LSTM effectively learns and remembers the complex long-term and short-term dependencies between hardening and salt penetration rates during the smoking process, ultimately extracting a high-dimensional feature vector from the sequence data that comprehensively represents the current smoking state. Finally, this feature vector is fed into the fully connected layer at the end of the LSTM network. This fully connected layer maps the high-dimensional feature space to a specific scalar value through linear weighted summation and an appropriate activation function (such as ReLU). This value is the more accurate and adaptive humidity adjustment value calculated by the model.

[0076] It should be noted that the training process of the aforementioned LSTM deep learning model is as follows: First, a training dataset needs to be constructed. This dataset comes from a large amount of historical optimal process data of the cured meat smoking process. Each data sample contains a hardening layer growth rate sequence and a salt penetration rate sequence within a time window, as well as the humidity adjustment value actually used after the window ends and verified as optimal, as training labels. Next, the dataset undergoes the same normalization and serialization preprocessing. During training, the mean squared error (MSE) is used as the loss function to measure the difference between the humidity adjustment value predicted by the model and the historical optimal humidity adjustment value. The backpropagation algorithm (such as the Adam optimizer) iteratively adjusts all weights and bias parameters in the LSTM network and the terminal fully connected layers, with the goal of minimizing the loss function. The training process continues until the model performs stably on an independent validation set and the prediction accuracy meets the requirements, thereby ensuring that the trained model can learn the deep nonlinear mapping relationship between complex process parameters and optimal humidity settings, rather than simply relying on a pre-set lookup table. This deep learning is another feasible embodiment for determining recommended humidity values, but it is not the focus of this application, so it will not be elaborated here.

[0077] Step S203: Control the humidifier to adjust the humidity inside the body to the recommended humidity value.

[0078] In some embodiments, step S203 includes: converting the recommended humidity value into a corresponding humidity control signal, and sending the humidity control signal to the humidifier corresponding to the main body via an industrial control bus; the humidifier adjusts its working state according to the corresponding humidity control signal until the monitored target environmental parameter reaches the recommended humidity value. Specifically, firstly, the control unit converts the calculated recommended humidity value into a corresponding humidity control signal. This signal is typically a standard industrial control signal, such as a 4-20mA analog current signal or a 0-10V voltage signal. Then, the humidity control signal is sent to the humidifier mounted on the side wall of the main body via an industrial control bus, such as PROFIBUS-DP or Modbus RTU. Next, the control circuit inside the humidifier receives the humidity control signal and parses it into a target humidity setpoint. Based on this, it automatically adjusts its operating state, for example, by adjusting the vibration frequency of the ultrasonic atomizing plate or the power of the heating element to change the humidification rate. During this adjustment process, the control unit continuously monitors the actual ambient humidity in the factory using the humidity sensor as feedback and compares it with the recommended humidity value, forming a closed-loop control loop until the actual ambient humidity stably reaches or infinitely approaches a stable condition determined by the recommended humidity value, thereby achieving precise humidity control.

[0079] It should be noted that the actual humidity data fed back by the humidity sensor needs to be continuously monitored and compared with the recommended humidity value. Only when the actual humidity data meets this stable condition can the system determine that an adjustment is complete; otherwise, it will continue to fine-tune the device's operating status until the environmental parameters meet the preset conditions.

[0080] It should be noted that the stable condition is not achieved instantaneously, but rather requires the ambient humidity to remain stable within a preset time period (such as 30 minutes). The specific criterion is that the humidity fluctuation does not exceed ±2% within 5 consecutive minutes.

[0081] By directly and automatically applying the calculated optimal target value to the execution equipment, a complete closed-loop control system is formed, which completely changes the traditional extensive management that relies on manual experience. It achieves high-precision and automated control of the smoking environment, ultimately ensuring that the smoking quality of each batch of cured meat is uniform and stable, and effectively avoiding quality defects such as local rot and dry outside and wet inside.

[0082] This invention, by monitoring the external environment while simultaneously monitoring the core internal and surface states of the cured meat itself, breaks through the limitations of traditional control methods that rely solely on environmental parameters. This provides indispensable multi-dimensional data support for accurately assessing the dynamic equilibrium of the smoking process, ensuring the comprehensiveness and scientific nature of control decisions from the outset. By dynamically converting state parameters into corresponding rates of change, it achieves a quantitative characterization of the complex smoking process, while also intuitively and dynamically revealing the trends and intensity of the smoking process, providing crucial feature inputs for risk warning and intelligent decision-making. By determining the existence of risks, it can identify risks before the dense, hardened shell actually forms and causes irreversible damage to the quality of the cured meat, gaining time for subsequent proactive intervention. The lookup table is based on... The construction of historical optimal process data ensures that the output target value is essentially a reuse of parameters from successful processes that have been verified in practice. This avoids unreliable outputs that may arise from complex models, guaranteeing the stability and reliability of the control effect. By comprehensively considering the dynamic changes in cured meat, the system ensures that the set humidity target value is highly matched with the actual processing requirements of the cured meat, thus achieving precise control. By directly and automatically applying the calculated optimal target value to the execution equipment, a complete closed-loop control system is formed. This completely changes the traditional extensive management that relies on manual experience, achieving precise control of the parameters of the cured meat smoking process. Ultimately, this ensures that the smoking quality of each batch of cured meat is uniform and stable, and effectively avoids quality defects such as localized rot and external dryness with internal dampness. Compared with existing technologies, this invention can achieve precise control of the parameters of the cured meat smoking process, thereby guaranteeing the quality of the cured meat.

[0083] Please refer to Figure 4To facilitate understanding, this application also provides a flowchart illustrating another embodiment of the parameter control method for the smoking process of cured meat. In this method, after collecting humidity data, the system first performs a crucial judgment: whether the current humidity is below a preset humidity threshold. If the judgment is "yes," it means the environment is too dry, which may cause premature hardening of the cured meat surface and affect the salt penetration process. At this point, the system immediately initiates a complex diagnostic mode and comprehensively analyzes the data acquired by the camera component and the infrared spectroscopy component to calculate two key process parameters: the growth rate of the hardened layer on the surface of the cured meat and the internal salt penetration rate.

[0084] The process then moves to its second critical decision point: determining whether there is a risk of surface hardening based on the two rates mentioned above (the hardening layer growth rate and the salt penetration rate). If the diagnosis is "yes," a risk is confirmed, and the process enters the precise adjustment phase. It uses the calculated hardening layer growth rate and salt penetration rate as input to query a lookup table built based on historical best process data, thus mapping a scientifically accurate humidity recommendation value. Ultimately, the system controls the humidifier to raise the ambient humidity to this target value to mitigate the risk and ensure the quality of the cured meat.

[0085] If the first judgment is "No" (i.e., humidity is not lower than the lower limit), or the second judgment is "No" (i.e., humidity is low but there is no risk of hardening after diagnosis), the process will not end. Instead, it will be uniformly merged into a high humidity check channel and a third judgment will be made, namely, whether the current humidity is higher than the preset upper humidity threshold. If the judgment is "Yes," it means that the environment is too humid, which may lead to problems such as mold growth even if there is no risk of hardening. At this time, the recommended dehumidification value will be directly calculated, and the dehumidifier will be controlled to actively reduce the humidity to a safe range. If the current humidity is neither lower than the lower limit nor higher than the upper limit, that is, it is in an ideal range, the system will determine "humidity is suitable, no adjustment is needed," and maintain the current operating state.

[0086] For example, the overall solution of this application can be understood using the following three scenarios: Scenario 1 (Too Low): The humidity sensor detects that the current humidity is 62% (<65%). The system immediately starts and, through camera and infrared spectral analysis, finds that the hardening rate is faster than the salt penetration rate, indicating a risk of hardening. It then queries the historical best data table and determines that the humidity needs to be increased to 70%. The control unit then starts the humidifier until the humidity reaches 70%. Scenario 2 (Suitable): The humidity is 68% (between 65% and 75%). The system detects that the humidity is above the lower limit, so it does not trigger a hardening risk diagnosis. Simultaneously, the humidity is also below the upper limit, so dehumidification is not initiated. The system maintains its current state, which is an ideal smoking environment. Scenario 3 (Too High): The humidity is 78% (i.e., greater than 75%). The system first checks if it is below the lower limit (65%); if not, it skips the complex hardening risk analysis. Then, it finds that the humidity exceeds the upper limit (75%), so it directly starts the dehumidifier to reduce the humidity to 75%.

[0087] Please refer to Figure 5 Based on the above method embodiments, this application also provides an apparatus embodiment, wherein this application further provides a smoking system, including a body 01, a control unit, a cured meat placement rack 03, an air inlet 04, an air outlet 02, a camera component 05, an infrared spectroscopy component (not shown in the figure), a humidity sensor (not shown in the figure), a humidifier 06, an exhaust fan 07, and a control unit; the humidity sensor, the camera component, the infrared spectroscopy component, the humidifier, and the exhaust fan are respectively signal-connected to the control unit; the control unit is used to implement the parameter control method for the cured meat smoking process as provided in Embodiment 1 of this application.

[0088] In some embodiments, the smoking system further includes: the cured meat racks are spaced apart inside the body; the air inlet is opened on the lower part of one side wall of the body; the air outlet is opened on the upper part of the other side wall of the body, forming an air circulation channel inside the body; the humidifier is located on the side wall of the body above the cured meat racks, and the dehumidifier is located on the inner wall of the body.

[0089] It should be noted that, Figure 5 The example given is merely one example of a dehumidifier, and this application does not limit the location of the dehumidifier.

[0090] In some embodiments, the humidity sensor is embedded in the inner wall of the main body and at a mid-height position near the cured meat rack, for collecting humidity values ​​within the main body; the camera assembly is fixed to the top of the main body by a bracket and directly opposite the placement area of ​​the cured meat rack, for obtaining the surface thickness value of the cured meat on the cured meat rack; the infrared spectroscopy assembly is installed on the side wall of the main body and at the same horizontal height as the cured meat rack, for obtaining the salt penetration depth of the cured meat.

[0091] It is understood that the above-described apparatus embodiments correspond to the method embodiments of the present invention, and can implement the parameter control method for the bacon smoking process provided by any of the above-described method embodiments of the present invention.

[0092] It should be noted that the device embodiments described above are merely illustrative, and some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Furthermore, in the accompanying drawings of the device embodiments provided by this invention, the connection relationships between modules indicate that they have communication connections, which can specifically be implemented as one or more communication buses or signal lines. Those skilled in the art can understand and implement this without any creative effort.

[0093] Based on the above-described embodiments of the parameter control method for the smoking process of cured meat, another embodiment of the present invention provides a terminal device, which includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, it implements the parameter control method for the smoking process of cured meat according to any embodiment of the present invention.

[0094] For example, in this embodiment, the computer program can be divided into one or more modules, which are stored in the memory and executed by the processor to complete the present invention. The one or more modules may be a series of computer program instruction segments capable of performing a specific function, which describe the execution process of the computer program in the terminal device.

[0095] The terminal device can be a desktop computer, laptop, handheld computer, or cloud server, etc. The terminal device may include, but is not limited to, a processor and a memory.

[0096] The processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor. The processor is the control center of the terminal device, connecting all parts of the terminal device via various interfaces and lines.

[0097] Based on the above-described method embodiments, another embodiment of the present invention provides a computer-readable storage medium, including a stored computer program, wherein, when the computer program is executed, it controls the device where the computer-readable storage medium is located to perform the parameter control method for the bacon smoking process described in any of the above-described method embodiments of the present invention.

[0098] The modules / units integrated in the device / terminal equipment, if implemented as software functional units and sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the above embodiments of the present invention can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0099] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A method for controlling parameters in a bacon smoking process, characterized in that, A control unit is used in a smoking system, the smoking system including a main body, a cured meat rack, an air inlet, an air outlet, a humidity sensor, a camera assembly, an infrared spectroscopy assembly, and a humidifier for increasing the humidity inside the main body, the control unit being connected to the humidifier, the humidity sensor, and the camera assembly respectively; The parameter control method includes: The humidity sensor collects the humidity value within the smoking system during the smoking process of cured meat. If the humidity value is less than a preset humidity threshold, the hardening layer growth rate of the cured meat surface is calculated based on the surface thickness value of the cured meat on the cured meat placement rack obtained by the camera component, and the salt penetration rate of the cured meat is calculated based on the salt penetration depth of the cured meat obtained by the infrared spectroscopy component. Based on the hardening layer growth rate and the salt penetration rate, it is determined whether there is a risk of surface hardening of the cured meat. If so, the hardening layer growth rate and the salt penetration rate are input into a pre-built lookup table to map and obtain the recommended humidity value for the current smoking process. The lookup table is constructed based on the historical optimal process data of the cured meat smoking process. The humidifier is controlled to adjust the ambient humidity within the body to the recommended humidity value.

2. The parameter control method for the smoking process of cured meat according to claim 1, characterized in that, The calculation of the salt penetration rate of cured meat based on the salt penetration depth obtained from the infrared spectroscopy component includes: The salt penetration depth of the cured meat is obtained through the infrared spectroscopy component, and the difference in salt penetration depth between adjacent sampling times is calculated based on the salt penetration depth. Based on the difference in salinity penetration depth, the initial salinity penetration rate is calculated respectively; The initial salt penetration rate was subjected to a moving average process to obtain the salt penetration rate inside the cured meat.

3. The parameter control method for the smoking process of cured meat according to claim 1, characterized in that, The calculation of the hardening layer growth rate of the cured meat surface based on the surface thickness value of the cured meat on the cured meat placement rack obtained by the camera component includes: The surface thickness value of the cured meat on the cured meat placement rack is obtained through the camera component; Identify outliers in the surface thickness value and remove them from the surface thickness value to obtain the processing result; The surface hardness difference between adjacent sampling times is calculated based on the processing results; Based on the surface hardness difference and the sampling time interval, the initial hardened layer growth rate is calculated. The initial hardened layer growth rate is smoothed and filtered to obtain the hardened layer growth rate.

4. The parameter control method for the smoking process of cured meat according to claim 1, characterized in that, The method of determining whether cured meat has a risk of surface hardening based on the hardening layer growth rate and the salt penetration rate includes: Calculate the time delay between the hardened layer growth rate and the salt penetration rate; Based on the time delay value, the time difference between the formation of the hardened layer and the salt penetration to the same depth is determined within several consecutive smoking periods. The time difference fluctuation amplitude sequence is calculated based on each of the aforementioned time difference values; Based on the time difference fluctuation amplitude sequence, the cumulative increment value of hardened layer thickness and the cumulative increment value of salt penetration depth are determined; The total cumulative difference between the cumulative increment of the hardened layer thickness and the cumulative increment of the salt penetration depth from the start of smoking to the current smoking time is determined, and the risk of surface hardening of the cured meat is judged based on the total cumulative difference.

5. The parameter control method for the smoking process of cured meat according to claim 1, characterized in that, The hardened layer growth rate and the salt penetration rate are input into a pre-built lookup table to map to a recommended humidity value for the current smoking process, including: The hardened layer growth rate and the salt permeation rate are mapped to corresponding discrete intervals to obtain the hardened layer growth rate interval and the salt permeation rate interval, respectively. Based on the combination of the hardened layer growth rate range and the salt penetration rate range, an index lookup is performed in the lookup table to obtain the recommended humidity value. The lookup table is determined based on a mapping relationship formed by associating the historically optimal smoking process parameters with the corresponding historical recommended humidity values.

6. The parameter control method for the smoking process of cured meat according to claim 1, characterized in that, The control of the humidifier to adjust the humidity inside the unit to the recommended humidity value includes: The recommended humidity value is converted into a corresponding humidity control signal, and the humidity control signal is sent to the humidifier corresponding to the main body via the industrial control bus; The humidifier adjusts its operating status according to the corresponding humidity control signal until the monitored target environmental parameters reach the recommended humidity value.

7. The parameter control method for the smoking process of cured meat according to any one of claims 1-6, characterized in that, The smoking system also includes a dehumidifier, and after determining whether the cured meat has a risk of surface hardening, it further includes: If there is no risk of surface hardening of the cured meat, then determine whether the humidity value is greater than the preset upper limit threshold humidity. If it is greater than the specified humidity value, a recommended dehumidification value is determined based on the humidity value and the preset upper limit threshold humidity. The dehumidifier is controlled to adjust the ambient humidity inside the body to the recommended dehumidification value.

8. A smoking system, characterized in that, The device includes a main body, a control unit, a cured meat rack, an air inlet, an air outlet, a humidity sensor, a camera assembly, an infrared spectroscopy assembly, a humidifier, an exhaust fan, and a control unit; the humidity sensor, the camera assembly, the infrared spectroscopy assembly, the humidifier, and the exhaust fan are respectively connected to the control unit; the control unit is used to implement the parameter control method for the cured meat smoking process as described in any one of claims 1-7.

9. The smoking system according to claim 8, characterized in that, The smoking system further includes: the cured meat racks are spaced apart inside the main body; the air inlet is located on the lower part of one side wall of the main body; the air outlet is located on the upper part of the other side wall of the main body, forming an air circulation channel inside the main body; the humidifier is located on the side wall of the main body above the cured meat racks, and the dehumidifier is located on the inner wall of the main body.

10. The smoking system according to claim 8, characterized in that, The humidity sensor is used to collect the humidity value inside the body; the camera component is used to obtain the surface thickness value of the cured meat on the cured meat rack; the infrared spectroscopy component is used to obtain the salt penetration depth of the cured meat.

Images