Informationized collaborative management system and method for kelp processing quality inspection

Abstract

The application relates to the field of food processing quality supervision information technology, and discloses a kelp processing quality inspection informationization collaborative management system and method, which comprises the following steps: a quality inspection data abstraction module acquires a detection parameter to generate a kelp quality state vector; a process dynamic alignment module calculates a quality state space-time attenuation factor according to transmission time delay and environmental humidity fluctuation and updates the kelp quality state vector; and a collaborative resource scheduling module solves a process quality deviation scalar and a data routing weight, wherein an embedded routing weight distribution module calculates a supervision tension index according to a process quality deviation scalar dynamic change rate and an absolute deviation amount, adaptively scales a sampling period according to a ratio and improves a data packet transmission priority, and inclines network bandwidth and computing power to a hidden danger process. The application eliminates process transmission lag and control fault, solves network congestion and response delay caused by static allocation, realizes closed-loop collaboration of quality inspection information and processing regulation, and has the advantages of high efficiency, high accuracy and high safety.

Description

Technical Field

[0001] This invention relates to an information-based collaborative management system and method for kelp processing quality inspection, belonging to the field of information technology for food processing quality supervision. Background Technology

[0002] Currently, large-scale industrial processing of kelp typically employs continuous production lines. Quality supervision and management mainly rely on quality inspection nodes set up at each process stage. Existing quality inspection information systems generally collect processing parameters for each process at fixed intervals and upload the quality inspection data to a central server through fixed data transmission paths for post-processing archiving and ledger management. This data collection method can meet basic quality traceability needs and is currently a relatively common management approach.

[0003] When kelp moves from one process to the next in a continuous processing pipeline, it undergoes a certain transmission time and environmental changes. Therefore, quality changes in the preceding process may continue to affect the subsequent process. Taking the connection between the desalination and drying processes as an example, existing management systems typically use a fixed data reporting frequency and allocate communication bandwidth evenly across all processes. When a local batch suddenly exhibits abnormal physicochemical indicators, other normal processes continue to upload large amounts of data, consuming the information network. Data uploaded by abnormal processes needs to queue, making it difficult for the central management unit to receive abnormal information and issue intervention commands in a timely manner. This situation, exacerbated by fixed communication bandwidth and management... The response delay caused by the allocation of computing power has become a major constraint on the operation of existing systems. To address the aforementioned management lag problem, the current improvement method is usually to increase the sampling frequency of all quality inspection nodes. However, comprehensively increasing the sampling frequency will increase the amount of data transmission and system maintenance costs. When multiple processes report data simultaneously, it will further aggravate the congestion of the underlying network. When the high-frequency data of the entire line is centrally entered into the management system, the delay in issuing core control commands may further increase. The main reason is that the existing system adopts a fixed and average allocation method for quality supervision resources, which makes it difficult to adjust according to the changes in the quality status of kelp with transmission time and environmental conditions.

[0004] Therefore, how to change the static allocation of management resources so that quality supervision can adapt to the dynamic changes in the quality status of kelp between processes and reduce the control delay caused by information overload has become the technical problem to be solved by this invention. Summary of the Invention

[0005] To address the problems in the background art, the technical solution of the present invention is as follows: A kelp processing quality inspection information-based collaborative management system, the system comprising: The quality inspection data abstraction module is used to obtain the detection parameters of each process and map them to generate a kelp quality state vector containing moisture characteristics, salinity characteristics, and physical morphological characteristics. The process dynamic alignment module is used to calculate the spatiotemporal attenuation factor of quality status based on the transmission delay between processes and the fluctuation amplitude of relative humidity, update the kelp quality status vector, and generate dynamic collaborative correction parameters between processes. The collaborative resource scheduling module is used to calculate the process quality deviation scalar, quality control threshold and data routing weight based on dynamic collaborative correction parameters. The collaborative resource scheduling module embeds a routing weight allocation module. The routing weight allocation module obtains the dynamic change rate and absolute deviation of the current process quality deviation scalar, and calculates the supervision tension index of the quality inspection data abstraction module. When the supervision tension index is higher than the average supervision tension index of the entire pipeline, it is determined that there is a risk of network congestion and management response delay, triggering an asymmetric scheduling rule. The basic quality inspection sampling period is scaled according to the ratio of the supervision tension index to the average supervision tension index of the entire pipeline, generating the actual dynamic sampling and reporting period of the quality inspection data abstraction module. This increases the data packet transmission priority of the quality inspection data abstraction module in the network communication link, tilting network bandwidth and management computing power to processes with potential quality problems, and eliminating associated risks.

[0006] Preferably, the specific processing logic for calculating the supervisory tension index by the routing weight allocation module is as follows: extract the dynamic change rate of the current process quality deviation scalar from the time series, wherein the dynamic change rate is obtained by dividing the difference between the process quality deviation scalar of the current scanning cycle and the process quality deviation scalar of the previous scanning cycle by the scanning time interval; assign a preset static deviation weight to the absolute deviation and a preset dynamic trend weight to the dynamic change rate; and aggregate the weighted absolute deviation and the weighted dynamic change rate to generate the supervisory tension index of the corresponding quality inspection data abstraction module.

[0007] Preferably, the specific processing logic of the routing weight allocation module for reconstructing the actual dynamic sampling and reporting cycle is as follows: determine the difference between the average supervision tension index of the entire pipeline and the supervision tension index of the current process; calculate the ratio of the difference to the average supervision tension index of the entire pipeline, and generate a dynamic adjustment ratio by combining the preset network bandwidth release coefficient; scale and map the preset basic quality inspection sampling cycle according to the dynamic adjustment ratio to generate the reconstructed actual dynamic sampling and reporting cycle of the current process.

[0008] Preferably, the preset basic quality inspection sampling period is set to 100ms, and the preset network bandwidth release coefficient is set to 0.6.

[0009] Preferably, the formula for calculating the spatiotemporal decay factor of quality status by the process dynamic alignment module is as follows: ,in, The spatiotemporal decay factor of the mass state. This is the batch transfer time difference between the current process and the previous process. This represents the amplitude of relative humidity fluctuations. The preset physicochemical attenuation constant of kelp, The preset time decay adjustment weight, This is the preset humidity interference compensation coefficient.

[0010] Preferably, the specific processing logic for the process dynamic alignment module to update the kelp quality state vector is as follows: obtain the first... Process up to the first The preset quality state transition matrix of the process and the inter-process environmental random disturbance compensation vector, where The processing step number is used; the attenuation factor is obtained by subtracting the spatiotemporal attenuation factor of the quality state from the base value 1; the quality state transition matrix and the... The process kelp quality state vector and the attenuation cofactor are multiplied together, and then the environmental random disturbance compensation vector is added to generate the first... The quality state vector of kelp after the process update.

[0011] Preferably, the quality inspection data abstraction module includes an acquisition interface unit and a vector construction unit; the acquisition interface unit acquires near-infrared spectral absorbance, conductivity, and optical imaging data; the vector construction unit converts the near-infrared spectral absorbance, conductivity, and optical imaging data into a normalized matrix based on a preset mapping matrix, and constructs a three-dimensional kelp quality state vector as the kelp quality state vector.

[0012] Preferably, the collaborative resource scheduling module further includes a control threshold generation module; the control threshold generation module calculates the process quality deviation scalar based on the updated kelp quality state vector; when the process quality deviation scalar exceeds the preset safety threshold, it generates an incremental control power adjustment instruction for the downstream process processing control unit based on the linear proportional mapping between the process quality deviation scalar and the preset control gain coefficient, and reconstructs the quality judgment critical point and processing control parameters of the downstream process.

[0013] Preferably, the collaborative resource scheduling module also includes a state anomaly backtracking module. When a certain process generates a continuous out-of-tolerance alarm signal, the state anomaly backtracking module extracts the historical time-series chain of the kelp quality state vector, reverse-engineers the quality state drift contribution rate of each preceding process in reverse order, locates the source processing process that triggered the continuous out-of-tolerance alarm signal, and locks the upper limit of the parameter operation of the processing control unit corresponding to the source processing process. The process dynamic alignment module is also used for environmental extreme fluctuation safety protection. When the amplitude of the relative humidity fluctuation exceeds the preset mutation threshold, the process dynamic alignment module sets the quality state spatiotemporal attenuation factor to zero, outputs an environmental anomaly alarm signal, and switches the collaborative resource scheduling module into the preset safety protection mode, limiting the calculated quality control threshold and the component values ​​of the kelp quality state vector of each process to a physically valid range of 0.0 to 1.0.

[0014] A method for information-based collaborative management of kelp processing quality inspection, used to run an information-based collaborative management system for kelp processing quality inspection, includes the following steps: Step S1: Obtain the detection parameters of each process through the quality inspection data abstraction module, and map them to generate a kelp quality state vector containing moisture characteristics, salinity characteristics and physical morphology characteristics. Step S2: The process dynamic alignment module calculates the spatiotemporal attenuation factor of quality status based on the transmission delay between processes and the fluctuation amplitude of relative humidity, updates the kelp quality status vector, and generates dynamic collaborative correction parameters between processes. Step S3: The collaborative resource scheduling module calculates the process quality deviation scalar, quality control threshold, and data routing weight based on the dynamic collaborative correction parameters. Step S4: Obtain the dynamic change rate and absolute deviation of the current process quality deviation scalar through the routing weight allocation module embedded in the collaborative resource scheduling module, and calculate the supervision tension index of the quality inspection data abstraction module. When the supervision tension index is higher than the average supervision tension index of the entire pipeline, it is determined that there is a risk of network congestion and management response delay. The asymmetric scheduling rule is triggered, and the basic quality inspection sampling period is scaled according to the ratio of the supervision tension index to the average supervision tension index of the entire pipeline. The actual dynamic sampling and reporting period of the quality inspection data abstraction module is generated, the data packet transmission priority of the quality inspection data abstraction module in the network communication link is increased, and the network bandwidth and management computing power are tilted to the process with quality risks, thereby eliminating the associated risks.

[0015] Compared with the prior art, the beneficial effects of the present invention are: 1. In the information-based collaborative management of kelp processing quality inspection, by combining the kelp quality state vector with the quality state spatiotemporal decay factor, the impact of inter-process transmission delay and environmental changes on the kelp quality state can be considered during the quality supervision process. This ensures the continuity of quality inspection information between upstream and downstream processes. By updating the kelp quality state vector, the gaps in quality inspection information that occur during material flow can be reduced, allowing downstream processes to obtain quality information that is more consistent with the current actual state. This improves the timeliness of inter-process collaborative control and reduces the risk of production batch quality decline caused by control lag.

[0016] 2. This invention calculates the monitoring tension index based on the absolute deviation and dynamic change rate of the process quality deviation scalar. It can simultaneously reflect the current degree of quality deviation and its changing trend, making it easy to identify processes with high risks that need to be prioritized. Based on this, the system adjusts the actual dynamic sampling and reporting cycle and data packet transmission priority, which can reduce the occupation of communication links by redundant data of normal processes, and make network bandwidth and management computing power prioritized for processes with potential quality problems. This alleviates network congestion and management response delays, and improves the efficiency of handling sudden quality anomalies.

[0017] 3. This invention can reallocate existing network bandwidth and management computing power based on the supervision tension index of each process without increasing communication hardware and computing equipment. By appropriately reducing the data reporting frequency of low-risk processes, communication resources can be freed up and used for data transmission and quality management of abnormal processes. This can improve the utilization efficiency of existing communication resources, reduce information overload caused by multiple processes reporting data simultaneously, and enable the system to transmit quality inspection data and issue control commands in a timely manner even in concurrent operation, thereby reducing blind spots in quality supervision and improving the stability of collaborative management processes. Attached Figure Description

[0018] Figure 1 This is a flowchart of the dynamic alignment of quality inspection data and resource scheduling in this invention; Figure 2 This is a diagram illustrating the dynamic alignment of quality inspection data and resource scheduling structure of this invention.

[0019] The objectives, features, and advantages of this invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0020] The technical solutions of the embodiments of this application will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments of this application are within the scope of protection of this application.

[0021] A collaborative information management system for quality inspection of kelp processing, the system comprising: The quality inspection data abstraction module is used to obtain the detection parameters of each process and map them to generate a kelp quality state vector containing moisture characteristics, salinity characteristics, and physical morphological characteristics. The process dynamic alignment module is used to calculate the spatiotemporal attenuation factor of quality status based on the transmission delay between processes and the fluctuation amplitude of relative humidity, update the kelp quality status vector, and generate dynamic collaborative correction parameters between processes. The collaborative resource scheduling module is used to calculate the process quality deviation scalar, quality control threshold and data routing weight based on dynamic collaborative correction parameters. The collaborative resource scheduling module embeds a routing weight allocation module. The routing weight allocation module obtains the dynamic change rate and absolute deviation of the current process quality deviation scalar, and calculates the supervision tension index of the quality inspection data abstraction module. When the supervision tension index is higher than the average supervision tension index of the entire pipeline, it is determined that there is a risk of network congestion and management response delay, triggering an asymmetric scheduling rule. The basic quality inspection sampling period is scaled according to the ratio of the supervision tension index to the average supervision tension index of the entire pipeline, generating the actual dynamic sampling and reporting period of the quality inspection data abstraction module. This increases the data packet transmission priority of the quality inspection data abstraction module in the network communication link, tilting network bandwidth and management computing power to processes with potential quality problems, and eliminating associated risks.

[0022] Preferably, the specific processing logic for calculating the supervisory tension index by the routing weight allocation module is as follows: extract the dynamic change rate of the current process quality deviation scalar from the time series, wherein the dynamic change rate is obtained by dividing the difference between the process quality deviation scalar of the current scanning cycle and the process quality deviation scalar of the previous scanning cycle by the scanning time interval; the absolute deviation is based on a preset static deviation weight, and the dynamic change rate is based on a preset dynamic trend weight; the weighted absolute deviation and the weighted dynamic change rate are numerically aggregated to generate the supervisory tension index of the corresponding quality inspection data abstraction module.

[0023] Preferably, the specific processing logic of the routing weight allocation module for reconstructing the actual dynamic sampling and reporting cycle is as follows: determine the difference between the average supervision tension index of the entire pipeline and the supervision tension index of the current process; calculate the ratio of the difference to the average supervision tension index of the entire pipeline, and generate a dynamic adjustment ratio by combining the preset network bandwidth release coefficient; scale and map the preset basic quality inspection sampling cycle according to the dynamic adjustment ratio to generate the reconstructed actual dynamic sampling and reporting cycle of the current process.

[0024] Preferably, the preset basic quality inspection sampling period is set to 100ms, and the preset network bandwidth release coefficient is set to 0.6.

[0025] Preferably, the formula for calculating the spatiotemporal decay factor of quality status by the process dynamic alignment module is as follows: ,in, The spatiotemporal decay factor of the mass state. This is the batch transfer time difference between the current process and the previous process. This represents the amplitude of relative humidity fluctuations. The preset physicochemical attenuation constant of kelp, The preset time decay adjustment weight, This is the preset humidity interference compensation coefficient.

[0026] Preferably, the specific processing logic for the process dynamic alignment module to update the kelp quality state vector is as follows: obtain the first... Process up to the first The preset quality state transition matrix of the process and the inter-process environmental random disturbance compensation vector, where The processing step number is used; the attenuation factor is obtained by subtracting the spatiotemporal attenuation factor of the quality state from the base value 1; the quality state transition matrix and the... The process kelp quality state vector and the attenuation cofactor are multiplied together, and then the environmental random disturbance compensation vector is added to generate the first... The quality state vector of kelp after the process update.

[0027] Preferably, the quality inspection data abstraction module includes an acquisition interface unit and a vector construction unit; the acquisition interface unit acquires near-infrared spectral absorbance, conductivity, and optical imaging data; the vector construction unit converts the near-infrared spectral absorbance, conductivity, and optical imaging data into a normalized matrix based on a preset mapping matrix, and constructs a three-dimensional kelp quality state vector as the kelp quality state vector.

[0028] Preferably, the collaborative resource scheduling module further includes a control threshold generation module; the control threshold generation module calculates the process quality deviation scalar based on the updated kelp quality state vector; when the process quality deviation scalar exceeds the preset safety threshold, it generates an incremental control power adjustment instruction for the downstream process processing control unit based on the linear proportional mapping between the process quality deviation scalar and the preset control gain coefficient, and reconstructs the quality judgment critical point and processing control parameters of the downstream process.

[0029] Preferably, the collaborative resource scheduling module also includes a state anomaly backtracking module. When a certain process generates a continuous out-of-tolerance alarm signal, the state anomaly backtracking module extracts the historical time-series chain of the kelp quality state vector, reverse-engineers the quality state drift contribution rate of each preceding process in reverse order, locates the source processing process that triggered the continuous out-of-tolerance alarm signal, and locks the upper limit of the parameter operation of the processing control unit corresponding to the source processing process. The process dynamic alignment module is also used for environmental extreme fluctuation safety protection. When the amplitude of the relative humidity fluctuation exceeds the preset mutation threshold, the process dynamic alignment module sets the quality state spatiotemporal attenuation factor to zero, outputs an environmental anomaly alarm signal, and switches the collaborative resource scheduling module into the preset safety protection mode, limiting the calculated quality control threshold and the component values ​​of the kelp quality state vector of each process to a physically valid range of 0.0 to 1.0.

[0030] A method for information-based collaborative management of kelp processing quality inspection, used to run an information-based collaborative management system for kelp processing quality inspection, includes the following steps: Step S1: Obtain the detection parameters of each process through the quality inspection data abstraction module, and map them to generate a kelp quality state vector containing moisture characteristics, salinity characteristics and physical morphology characteristics. Step S2: The process dynamic alignment module calculates the spatiotemporal attenuation factor of quality status based on the transmission delay between processes and the fluctuation amplitude of relative humidity, updates the kelp quality status vector, and generates dynamic collaborative correction parameters between processes. Step S3: The collaborative resource scheduling module calculates the process quality deviation scalar, quality control threshold, and data routing weight based on the dynamic collaborative correction parameters. Step S4: Obtain the dynamic change rate and absolute deviation of the current process quality deviation scalar through the routing weight allocation module embedded in the collaborative resource scheduling module, and calculate the supervision tension index of the quality inspection data abstraction module. When the supervision tension index is higher than the average supervision tension index of the entire pipeline, it is determined that there is a risk of network congestion and management response delay. The asymmetric scheduling rule is triggered, and the basic quality inspection sampling period is scaled according to the ratio of the supervision tension index to the average supervision tension index of the entire pipeline. The actual dynamic sampling and reporting period of the quality inspection data abstraction module is generated, the data packet transmission priority of the quality inspection data abstraction module in the network communication link is increased, and the network bandwidth and management computing power are tilted to the process with quality risks, thereby eliminating the associated risks.

[0031] Example 1: The current automated kelp production line sequentially includes washing, desalination, drying, and cutting / packaging processes. The physicochemical properties of kelp change with fluctuations in relative humidity and batch transport time. Quality control data abstraction modules distributed across each process acquire near-infrared spectral absorbance, conductivity, and optical imaging data through an acquisition interface unit. A vector construction unit normalizes the detection parameters based on a preset mapping matrix. This preset mapping matrix, determined through offline sampling data, includes three diagonal normalization scaling factors and corresponding bias adjustment terms. For near-infrared spectral absorbance, the measured absorption intensity at 940nm wavelength is divided by the standard water absorption peak value. The baseline offset is then subtracted to obtain the moisture characteristic between 0.0 and 1.0. For electrical conductivity, the electrical conductivity values ​​of 0 to 100 mS / cm collected by the high-frequency conductivity meter are subjected to linear extreme value transformation to obtain the salinity characteristic between 0.0 and 1.0. For optical imaging data, the kelp surface image is segmented into pixels, and the ratio of surface edge irregularity and wrinkle area is divided by the nominal area to obtain the physical morphology characteristic between 0.0 and 1.0. The vector construction unit arranges the normalized results into a three-row, one-column normalized matrix according to the order of moisture characteristic, salinity characteristic, and physical morphology characteristic, and uses this normalized matrix to construct a three-dimensional kelp quality state vector. ,in, , and They represent the first The process's moisture content, salt content, and physical properties. Indicates the sequence number of the processing step.

[0032] When a batch of materials is transferred from the desalination process to the drying process, the process dynamic alignment module receives the kelp quality state vector output by the desalination process. The batch transmission time difference is determined based on the batch timestamps of adjacent processes. And read the relative humidity fluctuation amplitude between processes. The process dynamic alignment module calls the physicochemical attenuation constant of kelp. Time decay adjustment weight Humidity interference compensation coefficient The spatiotemporal decay factor of the mass state is calculated according to the following formula: ,in, This represents the spatiotemporal decay factor of the mass state. This indicates the batch transfer time difference between the current process and the previous process. This indicates the amplitude of relative humidity fluctuations. This represents the preset physicochemical attenuation constant of kelp. This indicates the preset time decay adjustment weight. This indicates the preset humidity interference compensation coefficient. Subsequently, the process dynamic alignment module obtains the first... Process up to the first Preset quality state transition matrix of the process and inter-process environmental random disturbance compensation vector ,by As the decay cofactor, the kelp mass state vector is updated according to the following formula: ,in, Indicates the first The updated seaweed quality state vector after the process. Indicates the first Process up to the first Quality state transition matrix of the process, This represents the compensation vector for random environmental disturbances between processes. The process dynamic alignment module updates the kelp quality state vector. As a dynamic collaborative correction parameter between processes, it is output to the collaborative resource scheduling module for subsequent calculation of process quality deviation scalar, quality control threshold and data routing weight.

[0033] The control threshold generation module in the collaborative resource scheduling module receives dynamic collaborative correction parameters between processes. Based on the current process and the dominant quality characteristic, it selects the corresponding target setpoint and a preset safety threshold to form the quality control threshold for the current process. The target setpoint is used to calculate the process quality deviation scalar, and the preset safety threshold is used to determine whether to trigger processing control in subsequent processes. For the drying process, the control threshold generation module calculates the absolute deviations of moisture content, salt content, and physical morphology characteristics relative to their respective target setpoints, and uses weights of 0.70, 0.15, and 0.15 to determine the dominant quality characteristic. Since moisture content is the dominant quality characteristic of the drying process, the control threshold generation module takes the absolute value of the difference between the moisture content and the corresponding target setpoint as the process quality deviation scalar. The weighted deviation of salt content and physical morphology characteristics is used to verify the dominant quality characteristics. When both are within the normal control range, the scalar value of the process quality deviation is not changed. The value of .

[0034] The routing weight allocation module extracts the process quality deviation scalar of the current process from the time series. dynamic rate of change These are the absolute deviation and the rate of change of dynamic deviation, respectively, based on preset static deviation weights. With preset dynamic trend weights The monitoring tension index is calculated according to the following formula: ,in, This represents the supervisory tension index of the corresponding quality inspection data abstraction module. The absolute deviation of the process quality deviation scalar. This represents the dynamic rate of change of a scalar measure of process quality deviation. This represents the preset static deviation weight. This represents the preset dynamic trend weights; the data routing weights are determined by the supervisory tension index. Compared with the average monitoring tension index of the entire pipeline The ratio is obtained by linear mapping and is used to adjust the data packet distribution quota and queue queuing weight in the network communication link. When the supervision tension index of the current process is... Higher than the average monitoring tension index of the entire pipeline At this time, the routing weight allocation module determines that there is a risk of both network congestion and management response delay, triggers the asymmetric scheduling rule, and obtains the preset basic quality inspection sampling period. and preset network bandwidth release coefficient The actual dynamic sampling and reporting cycle for the current process is generated according to the following formula: ,in, This indicates the actual dynamic sampling and reporting cycle of the quality inspection data abstraction module. This indicates the preset basic quality inspection sampling cycle. This represents the preset network bandwidth release coefficient. This represents the average monitored tension index for the entire pipeline. This indicates the monitoring tension index of the current process. Processes with a monitoring tension index higher than the average monitoring tension index of the entire pipeline adopt a shorter actual dynamic sampling and reporting cycle, while processes with a monitoring tension index lower than the average monitoring tension index of the entire pipeline adopt a longer actual dynamic sampling and reporting cycle. This allows network bandwidth and management computing power to be allocated to processes with potential quality risks.

[0035] In the specific data calculation of this embodiment, the detection parameters at the outlet of the desalination process are normalized to form a kelp quality state vector. Batch transmission time difference The relative humidity fluctuation range is 180 seconds. The physicochemical attenuation constant of kelp is 5%. The time decay adjustment weight is 0.005 per second. The humidity interference compensation coefficient is 0.85. The value is 0.02. Substituting this value into the formula for calculating the spatiotemporal decay factor of mass state, we get... Combined with the mass state transition matrix Inter-process environmental random disturbance compensation vector The updated kelp quality state vector at the entrance of the drying process is obtained. Among them, moisture characteristic quantity The corresponding target setting is 0.4000, and the absolute value of the difference between the two is 0.0611. Therefore, the process quality deviation scalar value is... .

[0036] The routing weight allocation module calculates the supervisory tension index of the drying process quality inspection data abstraction module. The value was 0.85, which is higher than the average monitored tension index for the entire pipeline. 0.35; Supervisory Tension Index of the Washing Process Quality Inspection Data Abstraction Module The value is 0.12, representing the basic quality inspection sampling cycle. The network bandwidth release coefficient is 100ms. The value is 0.6. Based on the calculation formula for the actual dynamic sampling and reporting cycle, the actual dynamic sampling and reporting cycle for the drying process is... Adjusted to 14ms, the actual dynamic sampling and reporting cycle for the washing process. The time was adjusted to 139ms, so that the quality inspection data of the drying process is uploaded to the collaborative resource scheduling module in a shorter cycle, while keeping the total network communication bandwidth unchanged.

[0037] When the process quality deviation is scalar When the preset safety threshold is exceeded, the control threshold generation module controls the threshold based on the process quality deviation scalar. With preset control gain coefficient The linear proportional relationship generates control power adjustment increment commands. In this embodiment, a preset control gain coefficient is used. The calculated power adjustment increment is 50kW. The power output is 3.055kW. After receiving the instruction, the downstream processing control unit adjusts the power increment accordingly. The power setting of the drying process is corrected, the corrected power setting is written into the processing control parameters, and the corresponding quality judgment critical point is updated according to the power setting. The heat energy adjustment is completed before the kelp batch enters the drying process.

[0038] The packet transmission priority is adjusted through the industrial Ethernet protocol stack. The quality inspection data abstraction module writes the corresponding field value into the network service quality label in the Ethernet frame header. When the supervision tension index is higher than the average supervision tension index of the entire pipeline, the priority queue identifier corresponding to the switch port is increased from level 3 to level 7, and a high priority value is written into the differential service code point field of the network layer packet. This enables the LAN switch to use priority queue scheduling. Packets generated by processes with potential quality problems enter the high priority queue and are sent first. At the same time, the collaborative resource scheduling module increases the CPU scheduling priority of the corresponding data processing thread to the highest level and allocates network bandwidth and management computing power to this process.

[0039] The process dynamic alignment module continuously outputs the updated kelp quality status vector. Based on this, the collaborative resource scheduling module calculates the supervision tension index and adjusts the actual dynamic sampling and reporting cycle, data routing weight, and data packet transmission priority. The updated quality inspection data is used to generate control power adjustment increment instructions. After the downstream process processing control unit executes the instructions, it completes the adjustment of processing control parameters, thus forming a closed loop between quality inspection data acquisition, quality status update, supervision resource scheduling, and processing control.

[0040] Example 2: An experimental platform was built on an automated kelp processing line that includes washing, desalination, drying, and cutting / packaging processes. This platform was used to test the control response delay and quality control accuracy of the kelp processing quality inspection information collaborative management system during concurrent operation of multiple processes. The quality inspection data abstraction modules for each process were connected to a near-infrared spectrometer, a high-frequency conductivity meter, and an optical imaging acquisition module, respectively. The wavelength range of the near-infrared spectrometer was 800nm ​​to 2500nm, the measurement accuracy of the high-frequency conductivity meter was ±0.5%, and the resolution of the optical imaging acquisition module was 5 megapixels. Gaussian white noise with a signal-to-noise ratio of 20dB was superimposed on the detection parameters, and random ambient relative humidity fluctuations with an amplitude of 1.2% to 12.8% were applied in the inter-process transmission channel.

[0041] Basic quality inspection sampling cycle Set to 100ms to balance industrial Ethernet bus channel occupancy and the real-time nature of material detection; network bandwidth release coefficient. Set to 0.6 to limit the packet header overhead caused by excessively shortening the actual dynamic sampling and reporting cycle; static bias weight and dynamic trend weights The values ​​are set to 0.6 and 0.4 respectively, so that the monitoring tension index can simultaneously reflect the current process quality deviation and the trend of deviation change.

[0042] The experiment included the present invention sample group, control group A, control group B, and control group C. The present invention sample group adopted a complete information-based collaborative management system for kelp processing quality inspection; control group A adopted a fixed sampling period and a fixed routing mechanism; control group B retained the reconstruction process of the actual dynamic sampling and reporting period, but did not calculate the spatiotemporal decay factor of quality status. Control group C underwent the same processing procedure as the sample group of this invention, and the network bandwidth release coefficient was adjusted. Set to 1.2, different batch transfer time differences are set for 10 consecutive batches of kelp material between the desalination process outlet and the drying process inlet. and the amplitude of relative humidity fluctuation Simultaneously record detection parameters and kelp quality state vector. Spatial-temporal decay factor of mass state Process quality deviation scale Dynamic rate of change Supervisory Tension Index Actual dynamic sampling reporting cycle Queuing delay for control command issuance in network communication; power adjustment increment in control power adjustment increment commands. And the error in controlling the moisture content of the output.

[0043] In the sample of this invention, the process dynamic alignment module calculates the spatiotemporal attenuation factor of quality status based on the batch transmission time difference and the fluctuation amplitude of ambient relative humidity, updates the kelp quality status vector, and transmits the update result as a dynamic collaborative correction parameter between processes to the collaborative resource scheduling module. The collaborative resource scheduling module calculates the process quality deviation scalar and quality control threshold accordingly. The routing weight allocation module further calculates the supervision tension index, reconstructs the actual dynamic sampling and reporting cycle, and adjusts the data routing weight.

[0044] For batch B20260701, batch transmission time difference The relative humidity fluctuation amplitude is 120 seconds. The moisture content at the inlet of the drying process is 2.1% after the process dynamic alignment module updates the kelp quality state vector. The value is 0.5124; the collaborative resource scheduling module calculates the process quality deviation scalar. The supervised tension index is calculated to be 0.0245 by the routing weight allocation module. The value is 0.32, and the actual dynamic sampling reporting cycle is also included. The delay was adjusted to 105ms, the queuing time for issuing control commands for this batch was 2.1ms, and the output moisture control error was 0.32%.

[0045] For batch B20260702, batch transmission time difference Increased to 180s, ambient relative humidity fluctuation amplitude Increased to 5.0%, after quality status update, moisture characteristic value The value is 0.4611, representing the scalar value of process quality deviation. The supervisory tension index is 0.0611. The value is 0.85, and the routing weight allocation module uses this value to adjust the actual dynamic sampling and reporting cycle. The delay was adjusted to 14ms, the queuing time for issuing control commands was 2.4ms, and the output moisture control error was 0.41%.

[0046] For batch B20260703, batch transmission time difference The relative humidity fluctuation range is 240 seconds. The moisture content is 8.2%, as output by the process dynamic alignment module. The value is 0.4285, and the collaborative resource scheduling module calculates the process quality deviation scalar. The supervisory tension index is 0.0912. The actual dynamic sampling and reporting cycle is 0.94. The timeout was subsequently adjusted to 10ms, the control command issuance queue delay was 2.8ms, and the discharge moisture control error was 0.52%.

[0047] For batch B20260704, batch transmission time difference Relative humidity fluctuation amplitude reaches 300 seconds Reaching 10.5%, the updated moisture characteristic value The value is 0.4112, representing the scalar value of process quality deviation. The supervisory tension index is 0.1185. The value is 0.98, and the routing weight allocation module will dynamically sample and report the actual cycle. The control command issuance queue delay is 3.1ms, and the discharge moisture control error is 0.68%.

[0048] Control group A did not calculate the monitoring tension index, which was recorded as --. The sampling and reporting cycle for each process remained at 100ms. In batch B20260701, the batch transmission time difference was 120s, the relative humidity fluctuation amplitude was 2.1%, the moisture characteristic at the drying process inlet was 0.5842, the process quality deviation scalar was 0.0842, the control command issuance queuing delay was 18.5ms, and the discharge moisture control error was 1.85%. In batch B20260702, the batch transmission time difference was 180s, the relative humidity fluctuation amplitude was 5.0%, the moisture characteristic was 0.6210, and the process quality deviation scalar was 1.85%. The differential scalar value is 0.1210, the control command issuance queuing delay increases to 45.2ms, and the discharge moisture control error is 3.42%. In batch B20260703, the batch transmission time difference is 240s, the ambient relative humidity fluctuation amplitude is 8.2%, the moisture characteristic value is 0.6580, the process quality deviation scalar value is 0.1580, the control command issuance queuing delay reaches 82.6ms, and the discharge moisture control error is 5.18%. Fixed sampling and fixed routing cause the data of normal processes to continuously occupy the industrial Ethernet bus. The control commands of the drying process have a long queuing delay as the batch transmission time difference and the ambient relative humidity fluctuation amplitude increase.

[0049] Under the same input conditions corresponding to batch B20260702, the batch transmission time difference of control group B is 180s, and the ambient relative humidity fluctuation amplitude is 5.0%. Since the spatiotemporal decay factor of quality status is not calculated... The moisture content at the inlet of the drying process is 0.5312, the process quality deviation scalar is 0.0812, the monitoring tension index is 0.62, the actual dynamic sampling and reporting cycle is 54ms, the control command issuance queuing delay of this group is 8.6ms, and the discharge moisture control error is 2.15%. Although the actual dynamic sampling and reporting cycle has been adjusted according to the quality deviation, the kelp quality state vector has not been updated in time and space according to the batch transmission time difference and the fluctuation amplitude of the ambient relative humidity.

[0050] Control group C also used batch B20260702, with a batch transmission time difference of 180s, an ambient relative humidity fluctuation amplitude of 5.0%, a moisture characteristic of 0.4611, a process quality deviation scalar of 0.0611, a monitoring tension index of 0.85, an actual dynamic sampling and reporting cycle of 14ms. After the network bandwidth release coefficient was increased, the data packet header overhead increased, the control command issuance queuing delay reached 38.4ms, the discharge moisture control error was 2.88%, and the queuing state of the communication link showed a nonlinear deterioration inflection point.

[0051] In the aforementioned gradient operating conditions, the sample group of this invention updates the kelp quality state vector through the process dynamic alignment module, and the collaborative resource scheduling module adjusts the actual dynamic sampling and reporting cycle and data routing weight according to the supervision tension index. Data packets of processes with potential quality problems receive higher transmission priority, and network bandwidth and management computing power are allocated according to the changes in process quality state. This keeps the queuing delay for issuing control commands low even when the batch transmission time difference and the amplitude of relative humidity fluctuations increase. The results of the control group also show that fixed sampling and fixed routing, lack of spatiotemporal attenuation calculation of quality state, and excessively large network bandwidth release coefficients all increase the queuing delay of control commands or the error in the control of output moisture.

[0052] Example 3: The quality inspection data abstraction module of the current cutting and packaging process continuously monitors the kelp quality state vector. When the moisture content of three consecutive batches of materials... When all values ​​exceed the preset safety threshold of 0.4500, the system generates a continuous out-of-tolerance alarm signal. The status anomaly backtracking module then retrieves the time-series chain of the kelp quality status vector for the corresponding batch from the historical database, and extracts the kelp quality status vector for the drying process in reverse order of the process steps. Kelp quality state vector during desalination process The kelp quality state vector during the washing process .

[0053] The status anomaly backtracking module uses the moisture deviation in the cutting and packaging process as the backtracking benchmark, and first calculates the moisture characteristic of the drying process. The mean squared error drift is then used to calculate the salinity characteristics of the desalination process by forward-looking the coastal zone mass state vector time series chain. The mean square drift of the characteristic quantities corresponding to the washing process is also calculated. The mean square drift of each preceding process is mapped proportionally according to its proportion in the total drift of all preceding processes to obtain the quality state drift contribution rate. In the calculation results, the desalination process has a quality state drift contribution rate of 81.2% for the endpoint moisture exceeding the tolerance, and the washing process has a quality state drift contribution rate of 18.8%. Based on this, the desalination process is identified as the source processing process that triggers continuous out-of-tolerance alarm signals.

[0054] After determining the source processing procedure, the status anomaly backtracking module sends a parameter locking command to the desalination process processing control unit via the network, limiting the upper limit of the parameter operation of the soaking and cleaning valve opening to 65.0% of the rated position, thus preventing high-salt and high-moisture materials formed by insufficient desalination from continuing to enter the subsequent drying process.

[0055] Inter-process environmental sensors detected fluctuations in ambient relative humidity. When the mutation rate reaches 16.5% and exceeds the preset mutation threshold of 15.0%, the process dynamic alignment module activates the environmental extreme fluctuation safety protection, adjusting the quality status spatiotemporal decay factor. Set to zero, output an environmental anomaly alarm signal to the collaborative resource scheduling module, and cause the collaborative resource scheduling module to switch to security protection mode.

[0056] In the safety protection mode, the control threshold generation module generates quality control thresholds and the kelp quality state vector for the drying process. Moisture characteristics in Salt content characteristic amount and physical morphological characteristics By implementing boundary constraints, all values ​​are limited to a physically valid range of 0.0 to 1.0. The quality inspection data abstraction module continues to collect desensitized detection parameters and transmit quality inspection data according to a basic quality inspection sampling cycle of 100ms, so that the processing pipeline can maintain continuous monitoring during sudden changes in relative humidity.

[0057] When the relative humidity fluctuation exceeds 15.0%, the local water vapor partial pressure difference between the environmental medium and the kelp surface increases rapidly, and the material enters a non-equilibrium mass exchange state. The conventional exponential decay relationship can no longer fit the sudden nonlinear physicochemical changes. At this time, the spatiotemporal decay factor of the quality state is set to zero, the long-term prediction and extrapolation based on the steady-state exponential relationship is suspended, and the state prediction value of the previous process is frozen and transmitted to the entry of the next process as a temporary baseline under the safety protection mode. The collaborative resource scheduling module replaces the fitting and extrapolation data with high-frequency measured data collected by the quality inspection data abstraction module to avoid the overflow of calculated values ​​or the divergence of the kelp quality state vector caused by the drastic fluctuation of the relative humidity. The quality control threshold and the defined boundaries of each state component are maintained through the physical effective interval.

[0058] Example 4: This example combines Figures 1 to 2 This section explains the information-based collaborative management system and methods for kelp processing quality inspection, such as... Figure 1As shown, step S1 obtains the detection parameters of each process through the quality inspection data abstraction module, and maps them to generate a kelp quality state vector containing moisture characteristics, salinity characteristics, and physical morphological characteristics. Step S2 calculates the spatiotemporal decay factor of the quality state based on the inter-process transmission delay and the amplitude of relative humidity fluctuations, updates the kelp quality state vector, and generates inter-process dynamic collaborative correction parameters through the process dynamic alignment module. Step S3 calculates the process quality deviation scalar, quality control threshold, and data routing weight based on the dynamic collaborative correction parameters through the collaborative resource scheduling module. Step S4 allocates routing weights through the routing weights embedded in the collaborative resource scheduling module. The module acquires the dynamic change rate and absolute deviation of the current process quality deviation scalar, calculates the supervision tension index of the quality inspection data abstraction module, and determines the associated risk of network congestion and management response delay when the supervision tension index is higher than the average supervision tension index of the entire pipeline. It triggers the asymmetric scheduling rule, scales the basic quality inspection sampling period according to the ratio of the supervision tension index to the average supervision tension index of the entire pipeline, generates the actual dynamic sampling and reporting period of the quality inspection data abstraction module, improves the data packet transmission priority of the quality inspection data abstraction module in the network communication link, and tilts network bandwidth and management computing power to processes with potential quality problems, thereby eliminating associated risks.

[0059] like Figure 2 As shown, each process transmits the collected detection parameters to the mapping and generation of quality status stage. This stage outputs the kelp quality status vector to the calculation of the spatiotemporal attenuation factor stage. The inter-process environment inputs transmission delay and humidity fluctuations to the calculation of the spatiotemporal attenuation factor stage. This stage outputs the quality status spatiotemporal attenuation factor to the update of the quality status vector stage. The update of the quality status vector stage outputs the dynamically coordinated correction parameters to the quality deviation scalar calculation stage. Simultaneously, the update of the quality status vector stage inputs the kelp quality status vector into the historical time series chain. The quality deviation scalar calculation stage then... The process quality deviation scalar is output to the calculation and monitoring tension index stage. The quality deviation scalar stage simultaneously outputs the power adjustment increment command to the machining control unit. The monitoring tension index calculation stage outputs the monitoring tension index to the reconstruction sampling and reporting cycle stage. The reconstruction sampling and reporting cycle stage inputs the actual dynamic sampling and reporting cycle to the network communication link. The machining control unit feeds back the continuous out-of-tolerance alarm signal to the reverse simulation state drift stage. The historical time sequence chain inputs the historical time sequence chain to the reverse simulation state drift stage. The reverse simulation state drift stage outputs the lock parameter operating upper limit to the machining control unit.

[0060] Example 5: Before the system goes live, the process dynamic alignment module performs the following checks: Process up to the first Process quality state transition matrix Inter-process environmental random disturbance compensation vector Offline calibration was performed in a controlled environment transmission channel, using 50 standard material batches. The relative humidity fluctuation amplitude was also considered. Set to 0%, batch transfer time difference Hold for 180 seconds, and obtain the kelp mass state vectors at the outlet of the desalination process and the inlet of the drying process, respectively. and .

[0061] The process dynamic alignment module performs least-squares multiple linear regression on the offline sampled dataset to obtain the quality state transition matrix. Water transfer coefficient in the main diagonal of the matrix The salt transfer coefficient is 0.9800. The physical form transfer coefficient is 0.9500. The value is set to 1.0000, and all off-diagonal elements are set to 0.0000. Then, the mean residual vector between the measured kelp quality state vector at the drying process inlet and the matrix operation result is calculated, and this mean residual vector is determined as the inter-process environmental random disturbance compensation vector. , which serves as the initial parameter for the spatiotemporal update of the kelp quality state vector.

[0062] When performing general calibration of the quality state transition matrix and the inter-process environmental random disturbance compensation vector, at least 30 sets of data spanning different seasons and material batches are selected on a standard production line. Under the baseline working condition without environmental humidity difference, the kelp quality state vectors between adjacent processes are collected, and the corresponding state response relationship is calculated. The main diagonal elements of the quality state transition matrix reflect the intrinsic transfer rate of moisture, salinity, and physical morphology characteristics during the transfer between processes, while the off-diagonal elements reflect the cross-coupling relationship between each characteristic.

[0063] During the online operation of the system, the process dynamic alignment module periodically compares the updated kelp quality state vector with the actual collected vector at the entrance of the next process. When the mean residual of five consecutive material batches deviates from the original inter-process environmental random disturbance compensation vector by more than 10%, the main diagonal elements of the quality state transition matrix and the inter-process environmental random disturbance compensation vector are adjusted using the online recursive least squares method, so that the state update parameters are corrected as the physical characteristics of the raw material batches change.

[0064] The routing weight allocation module in the collaborative resource scheduling module completes the preset parameter calibration on a hardware-in-the-loop simulation test bench. The test bench is input with a discrete step-form process quality deviation scalar. and its dynamic rate of change Weight of static deviation Dynamic trend weights and network bandwidth release coefficient Perform parameter frequency sweep and static bias weighting. Set to 0.6, dynamic trend weight When set to 0.4, the supervisory tension index It can respond to sudden changes in process quality deviations while suppressing the incorrect adjustment of the actual dynamic sampling and reporting cycle caused by high-frequency Gaussian white noise.

[0065] Network bandwidth release coefficient When set to 0.6, the actual dynamic sampling and reporting cycle Compressed to 10ms, the industrial Ethernet bus load rate remains below the safe carrying threshold of 72.5%, thereby completing the pre-deployment calibration of dynamic sampling and reporting and data routing adjustment of the quality inspection data abstraction module.

[0066] Physicochemical attenuation constant of kelp The value of 0.005 seconds was obtained by measuring the evaporation kinetics of desalinated kelp in a constant temperature and humidity chamber. When the physicochemical decay constant of kelp is less than 0.001 seconds, the spatiotemporal decay factor of mass state is insufficient to respond to the changes in evaporation of kelp surface moisture; when it is greater than 0.02 seconds, the update result of kelp mass state vector is too sensitive to the batch transmission time difference.

[0067] Static Deviation Weight 0.6, dynamic trend weight The value of 0.4 is determined by the frequency sweep test in the frequency domain. When the static deviation weight accounts for a large proportion, the monitoring tension index takes the absolute deviation of the process quality deviation scalar as the main input. When the dynamic trend weight is higher than 0.5, the small noise in the detection parameters will cause the actual dynamic sampling and reporting cycle to fluctuate continuously.

[0068] Network bandwidth release coefficient The calibration value is 0.6, and its effective adjustment range is 0.2 to 0.8. When the network bandwidth release coefficient is lower than 0.2, the actual dynamic sampling and reporting cycle corresponding to the process with quality defects is not compressed enough, and the queuing delay for control command issuance exceeds 50ms. When it is higher than 0.8, the actual dynamic sampling and reporting cycle is compressed to less than 5ms, the overhead of industrial Ethernet data packet header increases, and a Layer 2 broadcast storm is caused. Through the above parameter calibration, the process dynamic alignment module and the collaborative resource scheduling module obtain the corresponding initial operating parameters before the system goes online.

[0069] Example 6: During the operation of the kelp automated processing line, the collaborative resource scheduling module performs link fault tolerance recovery based on the response confirmation signal of the communication link and the network packet loss rate. When a quality inspection data abstraction module does not receive a response confirmation signal from the collaborative resource scheduling module for three consecutive sampling cycles, the quality inspection data abstraction module starts the communication timeout interrupt procedure and reads the current actual dynamic sampling and reporting cycle. The adjustment ratio is determined based on the current network packet loss rate, and the actual dynamic sampling and reporting cycle is automatically extended to the basic quality inspection sampling cycle. It is 1.5 times faster, reducing the frequency of data packet transmission and alleviating the communication load of the industrial Ethernet bus.

[0070] The collaborative resource scheduling module continuously monitors the network packet loss rate of each communication link. When a link experiencing communication anomalies maintains a packet loss rate below 1.0% for 30 consecutive seconds, the routing weight allocation module removes the rate limiting state for that link and, based on the supervisory tension index... The real-time calculation results restore the actual dynamic sampling and reporting cycle. Dynamic adjustment.

[0071] The status anomaly backtracking module also employs a historical vector verification method based on a time-sliding window, setting the storage window for the kelp quality status vector to 60 seconds. When the kelp quality status vector of a certain process... When an isolated jump point occurs that exceeds three standard deviations of the normal fluctuation range, the kelp quality state vectors of the two adjacent sampling periods before and after the jump point are extracted. Median filtering correction is performed on the isolated jump point to eliminate instantaneous pulse false alarm signals caused by on-site electromagnetic interference, thus avoiding the mis-locking of the parameter operating limit of the processing control unit corresponding to the source processing process due to single-point abnormal data.

[0072] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0073] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A collaborative information management system for quality inspection of kelp processing, characterized in that the system... include: The quality inspection data abstraction module is used to obtain the detection parameters of each process and map them to generate a kelp quality state vector containing moisture characteristics, salinity characteristics, and physical morphological characteristics. The process dynamic alignment module is used to calculate the spatiotemporal attenuation factor of quality status based on the transmission delay between processes and the fluctuation amplitude of relative humidity, update the kelp quality status vector, and generate dynamic collaborative correction parameters between processes. The collaborative resource scheduling module is used to calculate the process quality deviation scalar, quality control threshold and data routing weight based on dynamic collaborative correction parameters. The collaborative resource scheduling module embeds a routing weight allocation module. The routing weight allocation module obtains the dynamic change rate and absolute deviation of the current process quality deviation scalar, and calculates the supervision tension index of the quality inspection data abstraction module. When the supervision tension index is higher than the average supervision tension index of the entire pipeline, it is determined that there is a risk of network congestion and management response delay, triggering an asymmetric scheduling rule. The basic quality inspection sampling period is scaled according to the ratio of the supervision tension index to the average supervision tension index of the entire pipeline, generating the actual dynamic sampling and reporting period of the quality inspection data abstraction module. This increases the data packet transmission priority of the quality inspection data abstraction module in the network communication link, tilting network bandwidth and management computing power to processes with potential quality problems, and eliminating associated risks.

2. The information-based collaborative management system for kelp processing quality inspection according to claim 1, characterized in that, The specific processing logic for calculating the supervisory tension index by the routing weight allocation module is as follows: Extract the dynamic change rate of the current process quality deviation scalar from the time series. The dynamic change rate is obtained by dividing the difference between the process quality deviation scalar of the current scanning cycle and the process quality deviation scalar of the previous scanning cycle by the scanning time interval. The absolute deviation is based on a preset static deviation weight, and the dynamic change rate is based on a preset dynamic trend weight. The weighted absolute deviation and the weighted dynamic change rate are numerically aggregated to generate the supervisory tension index of the corresponding quality inspection data abstraction module.

3. The information-based collaborative management system for quality inspection of kelp processing according to claim 1, characterized in that, The specific processing logic for reconstructing the actual dynamic sampling and reporting cycle in the routing weight allocation module is as follows: determine the difference between the average monitoring tension index of the entire pipeline and the monitoring tension index of the current process; calculate the ratio of the difference to the average monitoring tension index of the entire pipeline, and generate a dynamic adjustment ratio by combining the preset network bandwidth release coefficient; The preset basic quality inspection sampling cycle is scaled and mapped according to the dynamic adjustment ratio to generate the reconstructed actual dynamic sampling and reporting cycle of the current process.

4. The information-based collaborative management system for kelp processing quality inspection according to claim 3, characterized in that, The preset basic quality inspection sampling period is set to 100ms, and the preset network bandwidth release coefficient is set to 0.

6.

5. The information-based collaborative management system for kelp processing quality inspection according to claim 1, characterized in that, The formula for calculating the spatiotemporal decay factor of quality status in the process dynamic alignment module is as follows: ,in, The spatiotemporal decay factor of the mass state. This is the batch transfer time difference between the current process and the previous process. This represents the amplitude of relative humidity fluctuations. The preset physicochemical attenuation constant of kelp, The preset time decay adjustment weight, This is the preset humidity interference compensation coefficient.

6. The information-based collaborative management system for quality inspection of kelp processing according to claim 5, characterized in that, The specific processing logic for updating the kelp quality state vector in the process dynamic alignment module is as follows: obtain the first... Process up to the first The preset quality state transition matrix of the process and the compensation vector for random environmental disturbances between processes, where The processing step number is used; the attenuation factor is obtained by subtracting the spatiotemporal attenuation factor of the quality state from the base value 1; the quality state transition matrix and the... The process kelp quality state vector, the attenuation cofactor, and the environmental random disturbance compensation vector are multiplied together to generate the first... The quality state vector of kelp after the process update.

7. The information-based collaborative management system for kelp processing quality inspection according to claim 1, characterized in that, The quality inspection data abstraction module includes an acquisition interface unit and a vector construction unit. The acquisition interface unit acquires near-infrared spectral absorbance, conductivity, and optical imaging data. The vector construction unit converts the near-infrared spectral absorbance, conductivity, and optical imaging data into a normalized matrix based on a preset mapping matrix, and constructs a three-dimensional kelp quality state vector as the kelp quality state vector.

8. The information-based collaborative management system for kelp processing quality inspection according to claim 1, characterized in that, The collaborative resource scheduling module also includes a control threshold generation module; the control threshold generation module calculates the process quality deviation scalar based on the updated kelp quality state vector; when the process quality deviation scalar exceeds the preset safety threshold, it generates an incremental control power adjustment instruction for the downstream process processing control unit based on the linear proportional mapping between the process quality deviation scalar and the preset control gain coefficient, and reconstructs the quality judgment critical point and processing control parameters of the downstream process.

9. The information-based collaborative management system for quality inspection of kelp processing according to claim 1, characterized in that, The collaborative resource scheduling module also includes a status anomaly backtracking module. When a certain process generates a continuous out-of-tolerance alarm signal, the status anomaly backtracking module extracts the historical time-series chain of the kelp quality status vector, reverse-engineers the quality status drift contribution rate of each preceding process in reverse order, locates the source processing process that triggered the continuous out-of-tolerance alarm signal, and locks the upper limit of the parameter operation of the processing control unit corresponding to the source processing process. The process dynamic alignment module is also used for environmental extreme fluctuation safety protection. When the amplitude of the relative humidity fluctuation exceeds the preset mutation threshold, the process dynamic alignment module sets the quality status spatiotemporal attenuation factor to zero, outputs an environmental anomaly alarm signal, and switches the collaborative resource scheduling module into the preset safety protection mode, limiting the calculated quality control threshold and the component values ​​of the kelp quality status vector of each process to a physical effective range of 0.0 to 1.

0.

10. A method for information-based collaborative management of kelp processing quality inspection, used to run the information-based collaborative management system for kelp processing quality inspection as described in claim 1, characterized in that, Includes the following steps: Step S1: Obtain the detection parameters of each process through the quality inspection data abstraction module, and map them to generate a kelp quality state vector containing moisture characteristics, salinity characteristics and physical morphology characteristics. Step S2: The process dynamic alignment module calculates the spatiotemporal attenuation factor of quality status based on the transmission delay between processes and the fluctuation amplitude of relative humidity, updates the kelp quality status vector, and generates dynamic collaborative correction parameters between processes. Step S3: The collaborative resource scheduling module calculates the process quality deviation scalar, quality control threshold, and data routing weight based on the dynamic collaborative correction parameters. Step S4: Obtain the dynamic change rate and absolute deviation of the current process quality deviation scalar through the routing weight allocation module embedded in the collaborative resource scheduling module, and calculate the supervision tension index of the quality inspection data abstraction module. When the supervision tension index is higher than the average supervision tension index of the entire pipeline, it is determined that there is a risk of network congestion and management response delay. The asymmetric scheduling rule is triggered, and the basic quality inspection sampling period is scaled according to the ratio of the supervision tension index to the average supervision tension index of the entire pipeline. The actual dynamic sampling and reporting period of the quality inspection data abstraction module is generated, the data packet transmission priority of the quality inspection data abstraction module in the network communication link is increased, and the network bandwidth and management computing power are tilted to the process with quality risks, thereby eliminating the associated risks.

Images