Multi-temperature-area staged temperature monitoring management and alarm system for kelp drying

Abstract

The invention discloses a multi-temperature-zone staged temperature monitoring management and alarm system and method for kelp drying, and belongs to the technical field of temperature data processing, and the system comprises a temperature zone division module which is used for dividing a drying zone into four temperature zones and monitoring the temperature in real time through a temperature sensor, and a data acquisition module which is used for arranging distributed optical fiber sensors and transmitting the data to a data processing module. The system comprises a temperature acquisition module which acquires temperature data and performs dynamic error correction, a central control module which comprises a data fusion unit, a dynamic threshold calculation unit and a regulation and control instruction generation unit and is used for performing multi-scale noise reduction processing, dynamically updating the temperature threshold of each stage and generating a regulation and control instruction, and an alarm module which comprises a probability analysis unit and a thermodynamic constraint unit. The temperature overrun risk analysis module is used for analyzing the temperature overrun risk, and the power regulation and control module is used for adjusting the heating power of an overrun temperature area and adjusting the running speed of the conveying belt. According to the kelp drying system, the bottlenecks of a traditional drying system in precision, stability and energy efficiency are solved, and intelligence and high reliability of the kelp drying process are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of temperature data processing, and particularly relates to a multi-temperature zone staged temperature monitoring, management and alarm system for kelp drying. Background Art

[0002] As an important link in the field of agricultural product processing, the technology of kelp drying has evolved from traditional natural drying to modern mechanical drying. With the progress of sensor technology, automation control technology, and data processing technology, the kelp drying technology has gradually developed towards the direction of intelligence and refinement. However, there are still many deficiencies in the existing kelp drying systems in terms of temperature monitoring and management. Firstly, traditional drying systems often adopt single-temperature control, which cannot meet the differentiated temperature requirements of kelp in different drying stages, resulting in problems such as uneven drying, high energy consumption, and unstable product quality. Secondly, the temperature monitoring means of existing systems are relatively single, the data accuracy is not high, and there is a lack of an effective dynamic correction mechanism, making it difficult to achieve precise temperature control. In addition, most of the existing alarm systems are simple threshold alarms, unable to predict the risk of temperature exceeding the limit in advance, lacking compliance verification of the temperature field distribution, resulting in delayed alarms and greater potential safety hazards. Summary of the Invention

[0003] In view of the above existing problems, the purpose of the present invention is to achieve refined and intelligent control of the kelp drying process through multi-temperature zone division, distributed optical fiber sensor data acquisition, multi-scale noise reduction and dynamic threshold calculation of the central control module, probability analysis and thermodynamic constraint verification of the alarm module, and dynamic adjustment of PID parameters and optimization of the sliding mode control algorithm of the power regulation module.

[0004] To solve the above technical problems, a multi-temperature zone staged temperature monitoring, management and alarm system for kelp drying is proposed, including a temperature zone division module for dividing the drying area into four temperature zones, controlling the heating power through independent heating units, and real-time monitoring the temperature through temperature sensors; a data acquisition module for collecting the real-time temperature data of each temperature zone and dynamically correcting the errors of the main sensor data through a redundant correction unit; a central control module including a data fusion unit, a dynamic threshold calculation unit, and a control instruction generation unit for performing multi-scale noise reduction processing on the temperature data, dynamically updating the temperature thresholds at each stage, and generating control instructions; an alarm module including a probability analysis unit and a thermodynamic constraint unit for analyzing the risk of temperature exceeding the limit through a hidden Markov model and verifying the compliance of the temperature field distribution in combination with the heat conduction equation to trigger an alarm signal; a power regulation module for adjusting the heating power of the over-temperature zone according to the control instructions and synchronously adjusting the running speed of the kelp conveyor belt through linkage control.

[0005] As a preferred solution of a multi-temperature-zone staged temperature monitoring, management and alarm system for kelp drying according to the present invention, wherein: in the temperature zone division module, the preset temperature threshold ranges of each temperature zone are in a non-linear increasing sequence;

[0006] The drying area includes a preheating and warming zone, a balance and dehumidification zone, a warming and drying zone, and a cooling and shaping zone;

[0007] The threshold range setting step includes, according to the initial moisture content of kelp, fitting the exponential decay type threshold interval of the preheating and warming zone by the least square method, using a quadratic function model for the threshold interval of the balance and dehumidification zone, dynamically adjusting through the kelp drying rate and heat capacity parameters, and the threshold intervals of the warming and drying zone and the cooling and shaping zone are associated with the previous two temperature zones.

[0008] As a preferred solution of a multi-temperature-zone staged temperature monitoring, management and alarm system for kelp drying according to the present invention, wherein: in the data acquisition module, distributed optical fiber sensors are arranged according to a preset node distribution rule;

[0009] Arranging the distributed optical fiber sensors includes arranging main sensors along the conveyor belt direction according to the Legendre polynomial node distribution rule, the node spacing decreasing non-linearly with the length of the temperature zone, and adding redundant sensors at the end of the temperature zone. The data of the main sensors are dynamically corrected by the Kalman filtering algorithm, and the redundant sensor data are preferentially used to correct the measurement deviation of the main sensors. The corrected temperature data are uploaded to the data fusion unit of the central control module in real time;

[0010] The node spacing is expressed as:

[0011]

[0012] Wherein, is the spacing of the nth node, L is the length of the conveyor belt, N is the total number of nodes, and n is the current node number;

[0013] The formula for dynamically correcting the data of the main sensors is expressed as:

[0014]

[0015] Wherein, is the corrected temperature state estimation value at the current moment k, k and k - 1 are moment values, is the current temperature state estimation value predicted based on the previous moment, is the Kalman gain, is the actual temperature measurement value of the redundant sensor at the moment k, and H is the observation matrix.

[0016] As a preferred solution of a multi-temperature-zone staged temperature monitoring, management and alarm system for kelp drying according to the present invention, wherein: the central control module includes a data fusion unit, a dynamic threshold calculation unit and a regulation instruction generation unit;

[0017] The data fusion unit includes performing wavelet transform on multi-sensor data of the same temperature zone, decomposing it into high-frequency noise and low-frequency signals of different scales, screening effective signal components based on an adaptive threshold, reconstructing the temperature data after noise reduction, inputting the reconstructed data into the dynamic threshold calculation unit, and updating the temperature threshold range of each stage in combination with a fuzzy logic algorithm;

[0018] The regulation instruction generation unit includes calculating the difference between the real-time temperature and the dynamic threshold of each temperature zone to generate a temperature deviation signal. Based on historical data, when the temperature difference is greater than or equal to the temperature difference threshold, an emergency cooling instruction is generated, and when the temperature difference is less than the temperature difference threshold, a fine-tuning heating instruction is generated;

[0019] The formula for reconstructing the temperature data after noise reduction is:

[0020]

[0021]

[0022] Wherein, is the original temperature signal, is the temperature data after noise reduction, is the wavelet basis function, is the wavelet coefficient, is the indicator function, j is the scale parameter, g is the translation parameter, t is the time variable, is the adaptive threshold, is the noise standard deviation, U is the signal length, J is the total number of scales.

[0023] As a preferred solution of a multi-temperature-zone staged temperature monitoring, management and alarm method for kelp drying according to the present invention, wherein: the central control module further includes integrating a spatio-temporal convolutional neural network and training it;

[0024] Training the spatio-temporal convolutional neural network and applying it includes inputting the historical temperature sequences and regulation records of multiple temperature zones, constructing a training data set, extracting spatio-temporal features through the convolutional layer, predicting the future temperature change trend, and dynamically optimizing the temperature threshold and regulation response parameters according to the prediction results;

[0025] The loss optimization is expressed as:

[0026]

[0027] Wherein, A loss function for measuring the error between the predicted temperature and the actual temperature is the predicted temperature sequence is the actual temperature sequence is the norm of the vector is the regularization parameter is the total variation regularization term of the weight matrix W, where W is the weight matrix is the time point

[0028] As a preferred solution of the multi-temperature zone staged temperature monitoring, management and alarm system for kelp drying described in the present invention, wherein: the alarm module includes calculating the probability of current temperature exceeding the limit based on the hidden Markov model, verifying whether the temperature gradient satisfies the heat conduction equation constraint, discretely solving the temperature field distribution in the temperature zone by the finite element method, detecting local overheating or cold zone anomalies, and triggering an alarm signal and generating a control instruction when either the probability of exceeding the limit or the thermodynamic violation condition is satisfied;

[0029] Among them, the state transition probability is generated by training historical drying data, and the probability of current temperature exceeding the limit is fitted to the real-time temperature distribution through the Gaussian mixture model;

[0030] The formula for calculating the probability of current temperature exceeding the limit is:

[0031]

[0032] Among them, M is the number of states is the mixing weight of the Gaussian mixture model is the mean matrix of the m-th Gaussian component, i is the state index, and m is the Gaussian component index is the covariance matrix of the m-th Gaussian component is the Gaussian probability density function is the temperature value at time r, where r is time is the probability of current temperature exceeding the limit

[0033] The thermodynamic verification includes discretely solving the heat conduction equation by the finite element method and detecting whether the local temperature gradient is abnormal. The formula is expressed as:

[0034]

[0035] Among them, is the rate of change of temperature with time is the heat conduction coefficient is the Laplace operator of temperature is the internal heat source term, Z is temperature, and r is time; when the set threshold is reached, it is determined that the local temperature gradient is abnormal, and when When it is less than or equal to the set threshold, it is determined that the local temperature gradient is normal.

[0036] As a preferred solution of the multi-temperature zone staged temperature monitoring management and alarm system for kelp drying described in the present invention, the power control module includes calculating the proportional, integral and differential control quantities according to the temperature deviation, dynamically adjusting the PID parameters to adapt to the heat capacity characteristics of the temperature zone, introducing the sliding mode control algorithm to optimize the power adjustment quantity, and controlling the conveyor belt speed in a linked manner to synchronize the residence time of the kelp in the temperature zone with the heating power change;

[0037] The formula for dynamically adjusting PID parameters is expressed as:

[0038]

[0039] in, is the control quantity, i.e. the control signal output by the PID controller. is the proportional gain, i.e. the proportional term coefficient of PID control. is the integral gain, i.e. the integral term coefficient of PID control, is the differential gain, i.e. the differential term coefficient of PID control, is the deviation between the real-time temperature and the threshold, i.e. the error signal, r is the time, is the rate of change of the error signal, i.e. the differential of the error, is the variable index;

[0040] The sliding mode control algorithm is expressed as:

[0041]

[0042] in, is the gain coefficient, s is the sliding surface, i.e. the combination of error and integral, is the power adjustment amount, is a symbolic function;

[0043] The linkage control conveyor belt speed is expressed as:

[0044]

[0045] in, To adjust the conveyor belt speed, is the initial conveyor belt speed, is the maximum power, i.e. the maximum power output allowed by the system, is the power adjustment amount.

[0046] Another object of the present invention is to provide a multi-temperature zone phased temperature monitoring management and alarm method for kelp drying. The present invention solves the problems of insufficient temperature control accuracy, temperature fluctuations and instability, excessive energy consumption, low production efficiency, and safety and reliability in the traditional kelp drying system, and provides a more efficient, stable and safe solution for the kelp drying industry.

[0047] As a preferred solution of the multi-temperature zone phased temperature monitoring management and alarm method for kelp drying described in the present invention, it is characterized in that it includes dividing four independent temperature zones, initializing the heating unit and sensor parameters of each temperature zone, and collecting temperature data according to a preset node spacing through a distributed optical fiber sensor;

[0048] The central control module performs multi-scale decomposition and reconstruction on the original data, calculates the dynamic temperature threshold, compares the real-time temperature with the threshold, triggers an alarm and generates a regulation instruction when the limit is exceeded, adjusts the heating power through an adaptive controller, and synchronously controls the speed of the kelp conveyor belt.

[0049] A computer device includes a memory and a processor. The memory stores a computer program. It is characterized in that when the processor executes the computer program, the steps of the multi-temperature zone phased temperature monitoring management and alarm system for kelp drying described above are implemented.

[0050] A computer-readable storage medium stores a computer program thereon. It is characterized in that when the computer program is executed by a processor, the steps of the multi-temperature zone phased temperature monitoring management and alarm system for kelp drying described above are implemented.

[0051] Beneficial effects of the present invention: The present invention realizes refined zoning control of the drying area through the temperature zone division module. Each temperature zone independently controls the heating power and monitors the temperature in real time, ensuring that the kelp can obtain the optimal temperature environment at different drying stages, thereby improving the drying efficiency and quality and avoiding the problems of over-drying or under-drying; the data acquisition module improves the accuracy and reliability of temperature data through the optimized layout and dynamic error correction of distributed optical fiber sensors, provides high-quality data input for the central control module, and ensures the accuracy and effect of subsequent processing; the data fusion unit of the central control module effectively removes high-frequency noise and retains low-frequency effective signals through wavelet transform noise reduction processing of multi-sensor data, improves the signal-to-noise ratio of temperature data, and provides more accurate basic data for dynamic threshold calculation and control instruction generation; the dynamic threshold calculation unit dynamically updates the temperature threshold of each stage in combination with the fuzzy logic algorithm, realizing temperature The flexibility and adaptability of temperature control can adjust the control strategy according to the real-time situation, further optimize the drying process, and improve the drying quality of kelp; the integrated spatiotemporal convolutional neural network realizes the prediction of future temperature change trends, and dynamically optimizes the temperature threshold and control response parameters according to the prediction results, which enhances the foresight and initiative of the system and improves the accuracy and stability of temperature control; the probability analysis unit and thermodynamic constraint unit of the alarm module realize real-time analysis of temperature over-limit risks and compliance verification of temperature field distribution, and can timely detect and deal with local overheating or cold zone abnormalities, ensuring the safety and stability of the drying process; the power control module optimizes the power adjustment amount through the dynamic adjustment of PID parameters and the introduction of sliding mode control algorithm, and controls the conveyor belt speed in a linked manner, synchronizes the residence time of kelp in the temperature zone with the heating power change, realizes the refinement and intelligence of power control, and further improves the drying efficiency and quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work, among which:

[0053] Figure 1 A module schematic diagram of a multi-temperature zone staged temperature monitoring management and alarm system for kelp drying provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0054] To make the above objects, features, and advantages of the present invention more apparent and understandable, the following provides a detailed description of the specific embodiments of the present invention in conjunction with the accompanying drawings of the specification. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the scope of protection of the present invention.

[0055] In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention. However, the present invention may be implemented in other ways different from those described herein. Those skilled in the art can make similar generalizations without departing from the spirit of the present invention. Therefore, the present invention is not limited by the specific embodiments disclosed below.

[0056] Secondly, the so-called "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation manner of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it an embodiment that is mutually exclusive of other embodiments individually or selectively.

[0057] The present invention is described in detail in conjunction with schematic diagrams. When detailing the embodiments of the present invention, for ease of explanation, the cross-sectional views showing the device structure will be enlarged locally out of the general proportion, and the schematic diagrams are only examples and should not limit the scope of protection of the present invention herein. In addition, in actual production, three-dimensional spatial dimensions including length, width, and depth should be included.

[0058] Meanwhile, in the description of the present invention, it should be noted that the orientation or positional relationship indicated by terms such as "upper, lower, inner, and outer" is based on the orientation or positional relationship shown in the accompanying drawings. This is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation to the present invention. In addition, the terms "first, second, or third" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance.

[0059] Unless otherwise clearly defined and limited in the present invention, the terms "mounted, connected, and coupled" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can also be a mechanical connection, an electrical connection, or a direct connection, or can be indirectly connected through an intermediate medium, or can be the communication inside two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0060] Example 1, refer to Figure 1, which is the first embodiment of the present invention. This embodiment provides a multi-temperature zone stage temperature monitoring, management and alarm system for kelp drying, including: a temperature zone division module, a data acquisition module, a central control module, an alarm module and a power regulation module.

[0061] The temperature zone division module is used to divide the drying area into a preheating and warming zone, a balance dehumidification zone, a warming and drying zone and a cooling and shaping zone. Each temperature zone controls the heating power through an independent heating unit and monitors the temperature in real time through a temperature sensor;

[0062] In the temperature zone division module, the preset temperature threshold ranges of each temperature zone are a non-linear increasing sequence. Preheating and warming zone (zone one): temperature 50 - 55°C, kelp center temperature 50°C, high humidity in the box, the internal and external temperatures of the kelp are kept consistent to prevent the formation of a dense film on the surface and facilitate the next moisture removal; Balance dehumidification zone (zone two): temperature 55 - 60°C, adjust the air damper to control the wind speed, weakly extract moisture with a gentle wind, keep the humidity in the box low, remove moisture, and form tiny channels; Warming and drying zone (zone three): temperature 65 - 70°C, adjust the air damper to control the wind speed, strongly extract moisture and dry with a strong wind, realize waste heat recovery and enter the preheating and warming zone one for recycling; Cooling and shaping zone (zone four): temperature 50 - 55°C, adjust the air damper to control the wind speed, cool and shape to avoid deformation due to excessive dehydration.

[0063] The threshold range setting steps include fitting the exponential decay type threshold interval of the preheating and warming zone by the least square method according to the initial moisture content of the kelp, using a quadratic function model for the threshold interval of the balance dehumidification zone, dynamically adjusting through the kelp drying rate and heat capacity parameters, and the threshold intervals of the warming and drying zone and the cooling and shaping zone are related to the first two temperature zones.

[0064] It should be noted that through the non-linear increasing threshold, it is possible to avoid the cracking of the kelp surface or the residual moisture inside caused by sudden temperature changes, and solve the problem of uneven drying caused by traditional linear heating; the threshold of the subsequent stable temperature zone is related to that of the first two temperature zones to ensure smooth temperature transition, reduce the thermal stress generated by temperature zone switching, and improve the finished product rate of kelp.

[0065] The data acquisition module is used to arrange distributed optical fiber sensors according to the preset node distribution law, collect the real-time temperature data of each temperature zone, and perform dynamic error correction on the main sensor data through a redundancy correction unit;

[0066] In the data acquisition module, distributed optical fiber sensors are arranged according to the preset node distribution law;

[0067] The distributed optical fiber sensors are arranged as follows: the main sensors are arranged along the conveyor belt direction according to the distribution law of Legendre polynomial nodes, and the node spacing decreases non-linearly with the length of the temperature zone. Redundant sensors are added at the end of the temperature zone. The data of the main sensors are dynamically corrected by the Kalman filtering algorithm. The redundant sensor data is preferentially used to correct the measurement deviation of the main sensors, and the corrected temperature data is uploaded to the data fusion unit of the central control module in real time;

[0068] The node spacing is expressed as:

[0069]

[0070] Where, is the spacing of the nth node, L is the length of the conveyor belt, N is the total number of nodes, and n is the current node number;

[0071] The formula for dynamically correcting the data of the main sensors is expressed as:

[0072]

[0073] Where, is the estimated value of the corrected temperature state at the current time k, k and k - 1 are time values, is the estimated value of the current temperature state predicted based on the previous time, is the Kalman gain, is the actual measured value of the redundant sensor at time k, and H is the observation matrix.

[0074] Furthermore, the Legendre node layout optimizes the balance between dense sampling at the front end and sparse sampling at the end of the temperature zone, solving the problem of insufficient data at the end caused by traditional equidistant layout; the Kalman filtering correction preferentially corrects the errors at the end using the redundant sensor data, improving the reliability of the data in the end temperature zone (the end is vulnerable to environmental influences) and reducing the risk of misregulation.

[0075] The central control module includes a data fusion unit, a dynamic threshold calculation unit, and a control instruction generation unit, which are used to perform multi-scale noise reduction processing on the collected temperature data, dynamically update the temperature thresholds at each stage based on the fuzzy logic algorithm, and generate control instructions;

[0076] The central control module includes a data fusion unit, a dynamic threshold calculation unit, and a control instruction generation unit;

[0077] The data fusion unit includes performing wavelet transform on the multi-sensor data of the same temperature zone, decomposing it into high-frequency noise and low-frequency signals of different scales, screening the effective signal components based on the adaptive threshold, reconstructing the noise-reduced temperature data, inputting the reconstructed data into the dynamic threshold calculation unit, and updating the temperature threshold range at each stage in combination with the fuzzy logic algorithm;

[0078] The regulation instruction generation unit includes calculating the difference between the real-time temperature and the dynamic threshold of each temperature zone to generate a temperature deviation signal. Based on historical data, when the temperature difference is greater than or equal to the temperature difference threshold, an emergency cooling instruction is generated; when the temperature difference is less than the temperature difference threshold, a fine-tuning heating instruction is generated.

[0079] The formula for reconstructing the temperature data after noise reduction is:

[0080]

[0081]

[0082] Where, is the original temperature signal, is the temperature data after noise reduction, is the wavelet basis function, is the wavelet coefficient, is the indicator function, j is the scale parameter, g is the translation parameter, t is the time variable, is the adaptive threshold, is the noise standard deviation, U is the signal length, J is the total number of scales.

[0083] Furthermore, the central control module further includes integrating a spatio-temporal convolutional neural network and training it;

[0084] Training the spatio-temporal convolutional neural network and applying it includes inputting the historical temperature sequence and regulation records of multiple temperature zones, constructing a training dataset, extracting spatio-temporal features through the convolutional layer, predicting the future temperature change trend, and dynamically optimizing the temperature threshold and regulation response parameters according to the prediction results;

[0085] The loss optimization is expressed as:

[0086]

[0087] Where, is the loss function for measuring the error between the predicted temperature and the actual temperature, is the predicted temperature sequence, is the actual temperature sequence, is the norm of the vector, is the regularization parameter, is the total variation regularization term of the weight matrix W, W is the weight matrix, is the time point.

[0088] It should be noted that wavelet noise reduction separates high-frequency noise and effective signals, solves the problem of performance degradation of traditional filtering algorithms in non-stationary signals; and predicts future temperature changes through spatio-temporal features, adjusts the threshold and power in advance, and avoids overshoot or undershoot caused by lag response.

[0089] The alarm module includes a probability analysis unit and a thermodynamic constraint unit, which are used to analyze the risk of temperature exceeding the limit through a probability model, and verify the compliance of the temperature field distribution by combining with the heat conduction equation to trigger an alarm signal;

[0090] The alarm module includes calculating the probability of the current temperature exceeding the limit based on the hidden Markov model, verifying whether the temperature gradient satisfies the heat conduction equation constraint, discretely solving the temperature field distribution in the temperature zone by the finite element method, detecting local overheating or cold zone anomalies, and triggering an alarm signal and generating a regulation instruction when any one of the conditions of the exceeding limit probability or thermodynamic violation is met;

[0091] Among them, the state transition probability is generated by training historical drying data, and the current temperature exceeding limit probability is fitted to the real-time temperature distribution through the Gaussian mixture model;

[0092] The formula for calculating the current temperature exceeding limit probability is:

[0093]

[0094] Among them, M is the number of states, is the mixing weight of the Gaussian mixture model, is the mean matrix of the m-th Gaussian component, i is the state index, m is the Gaussian component index, is the covariance matrix of the m-th Gaussian component, is the Gaussian probability density function, is the temperature value at time r, r is the time, is the current temperature exceeding limit probability;

[0095] The thermodynamic verification includes discretely solving the heat conduction equation by the finite element method and detecting whether the local temperature gradient is abnormal. The formula is expressed as:

[0096]

[0097] Among them, is the rate of change of temperature with time, is the heat conduction coefficient, is the Laplace operator of temperature, is the internal heat source term, Z is the temperature, r is the time; when exceeds the set threshold, it is determined that the local temperature gradient is abnormal, and when is less than or equal to the set threshold, it is determined that the local temperature gradient is normal.

[0098] It should be noted that calculating the probability of the current temperature exceeding the limit based on the hidden Markov model solves the single-trigger problem of traditional threshold alarms, and the heat conduction equation constraint detects local temperature gradient anomalies (such as edge overheating or central cold zones), avoiding the global average from masking local risks.

[0099] The power regulation module is used to adjust the heating power of the over-temperature zone according to the regulation instruction, and synchronously adjust the running speed of the conveyor belt through the linkage control unit.

[0100] The power regulation module includes calculating the proportional, integral and differential control quantities according to the temperature deviation, dynamically adjusting the PID parameters to adapt to the heat capacity characteristics of the temperature zone, introducing a sliding mode control algorithm to optimize the power adjustment amount, and linking to control the conveyor belt speed to synchronize the residence time of the kelp in the temperature zone with the change of the heating power;

[0101] The formula for dynamically adjusting the PID parameters is expressed as:

[0102]

[0103] Among them, is the control quantity, that is, the control signal output by the PID controller, is the proportional gain, that is, the proportional term coefficient of the PID control, is the integral gain, that is, the integral term coefficient of the PID control, is the differential gain, that is, the differential term coefficient of the PID control, is the deviation between the real-time temperature and the threshold value, that is, the error signal, r is time, is the change rate of the error signal, that is, the differential of the error, is the variable index;

[0104] The sliding mode control algorithm is expressed as:

[0105]

[0106] Among them, is the gain coefficient, s is the sliding mode surface, that is, the combination of the error and the integral, is the power adjustment amount, is the sign function;

[0107] The linkage control of the conveyor belt speed is expressed as:

[0108]

[0109] Among them, is the adjusted conveyor belt speed, is the initial conveyor belt speed, is the maximum power, that is, the maximum power output allowed by the system, is the power adjustment amount.

[0110] Moreover, the sliding mode control can quickly converge to a stable state during sudden temperature changes, solving the oscillation problem of traditional PID in nonlinear systems; the conveyor belt speed linkage ensures that the residence time of kelp matches the power change, avoiding over-drying or under-drying in some areas caused by regulation delay.

[0111] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered within the scope of the claims of the present invention.

[0112] Embodiment 2, the second embodiment of the present invention, which is different from the previous embodiment in that:

[0113] If the above functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, the essence of the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes: USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical disks, etc., which can store program codes.

[0114] The logic and / or steps represented in the flowchart or described in other ways herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, which can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or in combination with these instruction execution systems, apparatus, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

[0115] More specific examples (nonexhaustive list) of computer-readable media include the following: electrical connections (electronic devices) having one or more wirings, portable computer disk cartridges (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber devices, and portable compact disc read-only memory (CDROM). Additionally, the computer-readable media can even be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpretation, or other suitable processing as necessary, and then stored in a computer memory.

[0116] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application-specific integrated circuits having suitable combinational logic gate circuits, programmable gate arrays (PGA), field programmable gate arrays (FPGA), etc.

[0117] Example 3 is the third embodiment of the present invention. This embodiment provides a multi-temperature-zone staged temperature monitoring, management, and alarm method for kelp drying, including dividing four independent temperature zones, initializing the heating unit and sensor parameters of each temperature zone, and collecting temperature data through a distributed fiber optic sensor at a preset node spacing.

[0118] The central control module performs multi-scale decomposition and reconstruction on the original data, calculates the dynamic temperature threshold, compares the real-time temperature with the threshold, triggers an alarm and generates a control instruction when the limit is exceeded, adjusts the heating power through an adaptive controller, and synchronously controls the speed of the kelp conveyor belt.

[0119] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not restrictive. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention, and they should all be covered by the scope of the claims of the present invention.

Claims

1. A multi-temperature-zone phased temperature monitoring, management and alarm system for kelp drying, characterized in that: A temperature zone division module, which is used to divide the drying area into four temperature zones, control the heating power through an independent heating unit, and monitor the temperature in real time through a temperature sensor; A data acquisition module, which is used to collect the real-time temperature data of each temperature zone, and dynamically correct the error of the main sensor data through a redundancy correction unit; A central control module, including a data fusion unit, a dynamic threshold calculation unit and a regulation instruction generation unit, which is used to perform multi-scale noise reduction processing on the temperature data, dynamically update the temperature thresholds of each stage, and generate regulation instructions; An alarm module, including a probability analysis unit and a thermodynamic constraint unit, which is used to analyze the risk of temperature exceeding the limit through a hidden Markov model, and verify the compliance of the temperature field distribution in combination with the heat conduction equation to trigger an alarm signal; A power regulation module, which is used to adjust the heating power of the temperature zone exceeding the limit according to the regulation instruction, and synchronously adjust the running speed of the kelp conveyor belt through linkage control.

2. The multi-temperature zone stage temperature monitoring, management and alarm system for kelp drying according to claim 1, characterized in that: In the temperature zone division module, the preset temperature threshold ranges of each temperature zone are a non-linear increasing sequence; The drying area includes a preheating and warming zone, a balance and dehumidification zone, a warming and drying zone and a cooling and shaping zone; The threshold range setting steps include fitting the exponential decay type threshold interval of the preheating and warming zone by the least square method according to the initial moisture content of the kelp, using a quadratic function model for the threshold interval of the balance and dehumidification zone, dynamically adjusting through the drying rate and heat capacity parameters of the kelp, and the threshold intervals of the warming and drying zone and the cooling and shaping zone are related to the first two temperature zones.

3. The multi-temperature zone stage temperature monitoring, management and alarm system for kelp drying according to claim 2, wherein: In the data acquisition module, distributed optical fiber sensors are arranged according to a preset node distribution rule; Arranging the distributed optical fiber sensors includes arranging the main sensors along the conveyor belt direction according to the node distribution rule of Legendre polynomials, the node spacing decreases non-linearly with the length of the temperature zone, and redundant sensors are added at the end of the temperature zone. The data of the main sensors are dynamically corrected through the Kalman filter algorithm, and the redundant sensor data is preferentially used to correct the measurement deviation of the main sensors, and the corrected temperature data is uploaded to the data fusion unit of the central control module in real time; The node spacing is expressed as: Among them, is the spacing of the nth node, L is the length of the conveyor belt, N is the total number of nodes, and n is the current node number; The formula for dynamically correcting the data of the main sensors is expressed as: Among them, is the estimated value of the corrected temperature state at the current time k, where k and k - 1 are time values, is the estimated value of the current temperature state predicted based on the previous time, is the Kalman gain, is the actual temperature measurement value of the redundant sensor at time k, and H is the observation matrix.

4. The multi-temperature zone stage temperature monitoring, management and alarm system for kelp drying according to claim 3, wherein: The central control module includes a data fusion unit, a dynamic threshold calculation unit and a regulation instruction generation unit; The data fusion unit includes performing wavelet transform on the multi-sensor data of the same temperature zone, decomposing it into high-frequency noise and low-frequency signals of different scales, screening the effective signal components based on an adaptive threshold, reconstructing the temperature data after noise reduction, inputting the reconstructed data into the dynamic threshold calculation unit, and updating the temperature threshold ranges of each stage in combination with the fuzzy logic algorithm; The regulation instruction generation unit includes calculating the difference between the real-time temperature and the dynamic threshold of each temperature zone to generate a temperature deviation signal. Based on historical data, when the temperature difference is greater than or equal to the temperature difference threshold, an emergency cooling instruction is generated, and when the temperature difference is less than the temperature difference threshold, a fine-tuning heating instruction is generated; The formula for reconstructing the temperature data after noise reduction is: Among them, is the original temperature signal, is the temperature data after noise reduction, is the wavelet basis function, is the wavelet coefficient, is the indicator function, j is the scale parameter, g is the translation parameter, and t is the time variable, is the adaptive threshold, is the noise standard deviation, U is the signal length, and J is the total number of scales.

5. The multi-temperature zone stage temperature monitoring, management and alarm system for kelp drying according to claim 4, characterized in that: The central control module also includes integrating a spatio-temporal convolutional neural network and training it; Training spatiotemporal convolutional neural networks and applying them include inputting historical temperature sequences and control records of multiple temperature zones, constructing training data sets, extracting spatiotemporal features through convolutional layers, predicting future temperature change trends, and dynamically optimizing temperature thresholds and control response parameters based on the prediction results; The loss optimization is expressed as: wherein, is a loss function for measuring the error between the predicted temperature and the actual temperature, is the predicted temperature sequence, is the actual temperature sequence, is the norm of the vector, is the regularization parameter, is the total variation regularization term of the weight matrix W, where W is the weight matrix, is the time point.

6. The multi-temperature zone stage temperature monitoring, management and alarm system for kelp drying according to claim 5, wherein: The alarm module includes calculating the probability of the current temperature exceeding the limit based on the hidden Markov model, verifying whether the temperature gradient satisfies the constraints of the heat conduction equation, discretely solving the temperature field distribution in the temperature zone through the finite element method, detecting local overheating or cold zone anomalies, and triggering an alarm signal and generating a control instruction when any condition of the probability of exceeding the limit or the thermodynamic violation is met; Among them, the state transition probability is generated by historical drying data training, and the current temperature over-limit probability is fitted by the Gaussian mixture model to fit the real-time temperature distribution; The formula for calculating the probability of the current temperature exceeding the limit is: where M is the number of states, is the mixing weight of the Gaussian mixture model, is the mean matrix of the m-th Gaussian component, i is the state index, and m is the Gaussian component index, is the covariance matrix of the m-th Gaussian component, is the Gaussian probability density function, is the temperature value at time r, where r is time, is the probability of current temperature exceeding the limit; Thermodynamic verification involves solving the heat conduction equation discretely using the finite element method to detect whether the local temperature gradient is abnormal. The formula is expressed as: wherein, is the rate of change of temperature with time, is the thermal conductivity, is the Laplacian operator of temperature, is the internal heat source term, Z is the temperature, and r is the time; when sets the threshold value, it is determined that the local temperature gradient is abnormal, and when is less than or equal to the set threshold value, it is determined that the local temperature gradient is normal.

7. The multi-temperature zone stage temperature monitoring, management and alarm system for kelp drying according to claim 6, characterized in that: The power control module includes calculating the proportional, integral and differential control quantities according to the temperature deviation, dynamically adjusting the PID parameters to adapt to the heat capacity characteristics of the temperature zone, introducing the sliding mode control algorithm to optimize the power adjustment quantity, and controlling the conveyor belt speed in a linked manner to synchronize the residence time of the kelp in the temperature zone with the heating power change; The formula for dynamically adjusting PID parameters is expressed as: Among them, is the control quantity, i.e., the control signal output by the PID controller, is the proportional gain, i.e., the proportional term coefficient of the PID control, is the integral gain, i.e., the integral term coefficient of the PID control, is the derivative gain, i.e., the derivative term coefficient of the PID control, is the deviation between the real-time temperature and the threshold value, i.e., the error signal, r is the time, is the change rate of the error signal, i.e., the derivative of the error, is the variable index; The sliding mode control algorithm is expressed as: Among them, is the gain coefficient, s is the sliding mode surface, that is, the combination of error and integral, is the power adjustment amount, is the sign function; The linkage control conveyor belt speed is expressed as: Among them, is the adjusted conveyor belt speed, is the initial conveyor belt speed, is the maximum power, that is, the maximum power output allowed by the system, is the power adjustment amount.

8. A multi-temperature zone staged temperature monitoring, management and alarm method for kelp drying, which is applied to the multi-temperature zone staged temperature monitoring, management and alarm system for kelp drying described in any one of claims 1-7, and is characterized in that: Including, dividing into four independent temperature zones, initializing the heating unit and sensor parameters of each temperature zone, and collecting temperature data through distributed optical fiber sensors according to the preset node spacing; The central control module performs multi-scale decomposition and reconstruction on the original temperature data, calculates the dynamic temperature threshold, and compares the real-time temperature with the threshold. When the limit is exceeded, an alarm is triggered and a control instruction is generated. The heating power is adjusted through the adaptive controller, and the speed of the kelp conveyor belt is controlled synchronously.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the steps of a multi-temperature zoned staged temperature monitoring management and alarm system for kelp drying according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, the steps of a multi-temperature zoned staged temperature monitoring management and alarm system for kelp drying according to any one of claims 1 to 7 are implemented.

Images