Rice deep processing monitoring system and method based on Internet of Things

Abstract

The invention discloses a rice deep processing monitoring system and method based on the Internet of Things, and relates to the technical field of rice deep processing, and the system comprises a data collection module, a data analysis module, a space calibration point obtaining module, a reference topology coefficient obtaining module and a real-time monitoring module. Analyzing whether the monitored cadmium form feature points belong to the corresponding cadmium form distribution space, calculating a position qualification rate and a monitoring topology coefficient so as to judge whether the cadmium form distribution is abnormal, and generating an abnormal distribution signal; real-time monitoring and accurate analysis of the cadmium form in the rice finish machining process are achieved, the abnormal cadmium content can be found in time, batch pollution is avoided, resource waste is reduced, the stability and safety of the machining process are further ensured, and the quality of rice products is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of rice deep processing, and in particular relates to a rice deep processing monitoring system and method based on the Internet of Things. Background Art

[0002] Cadmium contamination in rice is a major issue in the current food security field. Processing precision has a significant impact on the residual amount of cadmium in rice and its chemical forms. Cadmium is a non-essential heavy metal element. Long-term intake can cause health problems such as kidney damage and osteoporosis. The enrichment of cadmium in rice mainly comes from soil contamination and is often concentrated in the rice husk, aleurone layer and embryo. The form of cadmium in rice (such as inorganic cadmium, protein-bound cadmium, ester-soluble cadmium, etc.) has a decisive influence on its bioavailability (toxicity). The chemical forms of cadmium are divided into free cadmium, protein-bound cadmium and organic acid chelated cadmium.

[0003] Existing methods for detecting cadmium content in rice are usually offline laboratory tests, which have long cycles and high costs. Sampling tests are usually carried out after the product is processed, and real-time monitoring and early warning during the processing cannot be achieved. Once it is discovered that the product exceeds the standard, it often causes batch pollution, resulting in a large amount of waste of resources.

[0004] In addition, the bioavailability and toxicity of cadmium in different forms (such as Cd2+, CdS, Cd(OH)2, etc.) vary significantly. Monitoring only the total cadmium content cannot fully assess its potential risks to the human body. However, existing technologies have difficulty in achieving real-time online monitoring of multi-form cadmium during rice processing, accurately analyzing the dynamic distribution characteristics of cadmium in different processing links, and accurately quantifying and expressing the dynamic distribution characteristics of cadmium forms in multi-dimensional feature space. As a result, it is impossible to achieve intelligent judgment of abnormalities in the processing links, making rice quality control still remain in the post-remediation stage, and difficult to conduct accurate risk assessment. Based on this, a rice deep processing monitoring system and method based on the Internet of Things is proposed. Summary of the Invention

[0005] The purpose of the present invention is to provide a rice deep processing monitoring system and method based on the Internet of Things, which solves the technical problems that the existing technology is difficult to achieve real-time online monitoring of multiple forms of cadmium during rice deep processing and cannot accurately analyze the dynamic distribution characteristics of cadmium in different processing links.

[0006] The Internet of Things-based rice deep processing monitoring system includes:

[0007] Step 1: Obtain the historical content data of each form of cadmium at each stage in the rice processing process;

[0008] Step 2: Analyze the historical content data of each form of cadmium at each link in the rice processing process to obtain the distribution space of the cadmium forms corresponding to each processing link;

[0009] Step 3: Based on the cadmium morphological characteristic points corresponding to each finishing step during the processing of multiple batches of rice, the spatial calibration points corresponding to each finishing step are analyzed;

[0010] Step 4: Analyze the cadmium morphological characteristic points and spatial calibration points corresponding to each finishing step of multiple batches of rice to obtain the corresponding benchmark topological coefficients within each finishing step;

[0011] Step 5: Acquire multiple monitoring cadmium morphological characteristic points of rice within the monitoring link, analyze whether each monitoring cadmium morphological characteristic point belongs to the cadmium morphological distribution space of the corresponding monitoring link, obtain the position qualification rate corresponding to the monitoring link, obtain the monitoring topology coefficient based on multiple monitoring cadmium morphological characteristic points, and determine the generation of abnormal distribution signals based on the position qualification rate and monitoring topology coefficient of rice in the monitoring link.

[0012] As a further solution of the present invention, the specific method of obtaining the cadmium form distribution space corresponding to each finishing step is:

[0013] Select one of the multiple finishing links as the target link without replacement; obtain historical content data of various forms of cadmium at the target link points in the processing of multiple batches of rice, obtain historical content data Gi (GAi, GBi, GCi) of various forms of cadmium corresponding to the target link when multiple batches of rice are processed, obtain the maximum values GAmax, GBmax and GCmax of different forms of cadmium GAi, GBi and GCi in all batches, normalize Gi (GAi, GBi, GCi) by GHi (GAi / GAmax, GBi / GBmax, GBi / GCmax), obtain the cadmium morphological feature points GHi corresponding to each batch in the target link, perform discretization complex analysis on each cadmium morphological feature point GHi, and generate the cadmium morphological distribution space Q1 corresponding to the target link, where i refers to different processing batches, i = 1, 2, ..., n, n refers to the total number of batches, GAi, GBi and GCi refer to different forms of cadmium;

[0014] By adopting the same analysis method, the cadmium form distribution space Qb corresponding to each finishing link can be obtained, where b refers to different finishing links, b = 1, 2, ..., r, where r refers to the total number of finishing links.

[0015] As a further solution of the present invention, the specific method of performing discretization complex analysis on each cadmium morphological feature point GHi is:

[0016] Taking the cadmium morphological feature point GHi as the center, the mean Gp of the distances between all cadmium morphological feature points and the standard deviation of the distances between all batch feature points are obtained according to GHi (GAi / GAmax, GBi / GBmax, GBi / GCmax). The sum of the mean Gp and 2 times the standard deviation is used as the preset radius β, that is, β=Gp+2Gp. A sphere is drawn according to the preset radius β to obtain multiple spheres Ai corresponding to the covering complex Fi respectively. The union of the geometric areas covered by each sphere Ai is used as the cadmium morphological distribution space Q1 corresponding to the target link.

[0017] As a further solution of the present invention, the specific method of obtaining the spatial calibration points corresponding to each finishing step is:

[0018] First, obtain the mean values of each cadmium morphological characteristic data GAi / GAmax, GBi / GBmax and GBi / GCmax in the cadmium morphological characteristic points GHi (GAi / GAmax, GBi / GBmax, GBi / GCmax) corresponding to each batch in the target link, and then obtain the spatial calibration point B1 (BA, BB, BC) corresponding to the target link: adopt the same analysis method to obtain the spatial calibration point Bb corresponding to each finishing link.

[0019] As a further solution of the present invention, the reference topology coefficients corresponding to each finishing step are obtained in the following manner:

[0020] Obtain the cadmium morphological characteristic points GHi (GAi / GAmax, GBi / GBmax, GBi / GCmax) corresponding to each batch in the target link and the spatial calibration points B1 (BA, BB, BC) corresponding to the target link;

[0021] The distance Di between each cadmium morphological feature point and the spatial calibration point is calculated by the distance formula. According to the preset radius β, the cadmium morphological distribution space Q1 corresponding to the target link is divided into a spherical neighborhood with the spatial calibration point B1 as the center as the calibration point B1 neighborhood. The cadmium morphological feature points with a distance Di less than or equal to the preset radius β are determined as feature points falling into the calibration point B1 neighborhood. The number of feature points e falling into the calibration point B1 neighborhood is counted and the number e is compared with the calibration point B1 neighborhood volume V. B1 The ratio between them is taken as the neighborhood density P corresponding to the target link B1 ; through T1 = α × P B1+(1-α), calculate the benchmark topology coefficient T1 corresponding to the target link, and α takes a value of 0.5 to 0.7; use the same analysis method as that for obtaining the benchmark topology coefficient T1 corresponding to the target link to obtain the benchmark topology coefficient Tb corresponding to each finishing link.

[0022] As a further solution of the present invention: obtain the neighborhood volume V of the calibration point B1 B1 The specific ways are:

[0023] pass Get the neighborhood volume V of the calibration point B1 B1 .

[0024] As a further solution of the present invention: the specific method of determining the generation of abnormal distribution signals is:

[0025] The real-time data of various forms of cadmium in rice were obtained multiple times to obtain the characteristic points GHg of each monitored cadmium form. 实时 , where g refers to different acquisition times, g = 1, 2, ..., y, y is a positive integer greater than 1, obtain the spatial calibration points corresponding to the real-time monitoring link, and calculate the morphological characteristic points GHg of each monitoring cadmium 实时 The distance Lg between each of the spatial calibration points corresponding to the monitoring link is respectively determined. When Lg is less than or equal to the preset radius β, it is determined that the corresponding monitoring cadmium morphological characteristic point belongs to the cadmium morphological distribution space corresponding to the real-time monitoring link. When L is greater than the preset radius β, the corresponding monitoring cadmium morphological characteristic point does not belong to the cadmium morphological distribution space corresponding to the real-time monitoring link. The ratio between the number f of monitoring cadmium morphological characteristic points belonging to the cadmium morphological distribution space corresponding to the real-time monitoring link and the number of acquisitions g is obtained as the position qualification rate JA corresponding to the real-time monitoring link. The same calculation and analysis method as that for obtaining the benchmark topological coefficient T1 corresponding to the target link is adopted. Calculate and obtain the monitoring topology coefficient JB corresponding to the monitoring link, obtain the absolute value JD of the difference between the benchmark topology coefficient and the monitoring topology coefficient corresponding to the monitoring link, calculate the sum of the reciprocal of the position qualification rate JA corresponding to the real-time monitoring link and the product of the absolute value JD of the difference and the preset value coefficients ω1 and ω2, and use it as the reasonable coefficient HL corresponding to the monitoring link. The specific values of the preset value coefficients ω1 and ω2 are formulated by relevant personnel according to actual needs, satisfying 1=ω1+ω2, ω1<ω2. When the reasonable coefficient HL is greater than the preset value Y1, an abnormal distribution signal is generated. Otherwise, no processing is performed.

[0026] The method for monitoring rice deep processing based on the Internet of Things comprises the following steps:

[0027] Step 1: Obtain the historical content data of each form of cadmium at each stage in the rice processing process;

[0028] Step 2: Analyze the historical content data of each form of cadmium at each link in the rice processing process to obtain the distribution space of the cadmium forms corresponding to each processing link;

[0029] Step 3: Obtain the spatial calibration points corresponding to each finishing step;

[0030] Step 4: Obtain the corresponding benchmark topology coefficients in each finishing step;

[0031] Step 5: Acquire and analyze multiple monitoring cadmium morphological characteristic points of rice in the monitoring link, obtain the position qualification rate corresponding to the monitoring link, obtain the monitoring topology coefficient, and determine the generation of abnormal distribution signals based on the position qualification rate and monitoring topology coefficient of rice in the monitoring link.

[0032] Compared with the prior art, the present invention has the following beneficial effects:

[0033] The present invention maps the content data of different forms of cadmium in rice to a multidimensional feature space, constructs a distribution space and spatial calibration points covering the distribution characteristics of cadmium forms based on historical health data, and further constructs a benchmark topological coefficient capable of quantifying the degree of distribution aggregation and uniformity; finally, the position qualification rate and the real-time monitoring topological coefficient are calculated through real-time data, and the weighted fusion is performed to form a comprehensive and reasonable coefficient, and the threshold value of the coefficient is used to judge and realize intelligent early warning of abnormal distribution of cadmium forms; the real-time and multi-dimensional monitoring of cadmium forms in the rice finishing process is realized, and a health distribution benchmark based on topological characteristics can be quantitatively established. On this basis, by comprehensively considering the spatial position conformity and the topological structure deviation, intelligent judgment of abnormal distribution of cadmium forms is realized, and an abnormal distribution signal is generated; the real-time monitoring of cadmium forms in the rice finishing process is realized, and the rice finishing level is effectively improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 Schematic diagram of the system framework structure of the present invention;

[0035] Figure 2 Schematic diagram of the framework structure of the method of the present invention. DETAILED DESCRIPTION

[0036] The technical solutions of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0037] Example 1: Please refer to Figure 1,This application provides a rice deep processing monitoring system based on the Internet of Things, including;

[0038] The data acquisition module obtains the historical content data of each form of cadmium at each link in the rice processing process;

[0039] It should be noted that each link refers to the end of each link, and sensors that can provide quasi-real-time total cadmium content or indicative heavy metal information are deployed. For example, online X-ray fluorescence spectrometers or laser-induced breakdown spectrometers can provide elemental content information. Although they cannot directly distinguish the forms, they can serve as preliminary warnings. For rapid form analysis, electrochemical detectors / spectral detectors based on microfluidic chips, electrochemical sensor arrays, or combined with rapid chromatographic separation are introduced to achieve minute-level cadmium form analysis. By combining the two, the content of cadmium in various forms can be monitored. The above technologies are all existing and mature, so they are not described in detail here.

[0040] The data acquisition module captures historical cadmium speciation data at each stage of rice processing. Near-real-time monitoring of cadmium speciation is achieved using sensor technologies such as online X-ray fluorescence spectrometry and laser-induced breakdown spectrometry, combined with microfluidic chips and electrochemical sensor arrays.

[0041] The data analysis module analyzes the historical content data of each form of cadmium at each link in the rice processing process to obtain the distribution space of the cadmium forms corresponding to each link. The specific method is as follows:

[0042] Select one of the multiple finishing links as the target link without replacement;

[0043] Obtain the historical content data of each form of cadmium in rice at the target link when multiple batches of rice are processed. Obtain the historical content data of each form of cadmium in rice at the target link when multiple batches of rice are processed. Mark them as Gi (GAi, GBi, GCi), where i refers to different processing batches, GAi, GBi and GCi refer to different forms of cadmium (for example, GA refers to Cd 2+ , GB is CdS, GC is Cd(OH)2);

[0044] Obtain the maximum values GAmax, GBmax, and GCmax of cadmium forms GAi, GBi, and GCi in all batches, respectively, and normalize Gi(GAi, GBi, GCi) by GHi(GAi / GAmax, GBi / GBmax, GBi / GCmax);

[0045] Obtain the cadmium morphological feature points GHi corresponding to each batch in the target link. After performing discretization complex analysis on each cadmium morphological feature point GHi, generate the cadmium morphological distribution space Q1 corresponding to the target link. The specific method is as follows:

[0046] With the cadmium morphological feature point GHi as the center, a sphere is drawn according to the preset radius β, and then multiple spheres Ai are obtained, which correspond to the covering complex Fi: Fi = {(GHi, β)|i = 1, 2, ..., n}, where i refers to different processing batches and n refers to the total number of batches;

[0047] The union of the geometric areas covered by the corresponding complex F is used as the cadmium morphology distribution space Q1 corresponding to the target link, that is,

[0048] The preset radius β is determined as follows;

[0049] According to GHi (GAi / GAmax, GBi / GBmax, GBi / GCmax), the mean Gp of the distances between feature points of all batches and the standard deviation U of the distances between feature points of all batches are obtained. The sum of the mean Gp and 2 times the standard deviation is used as the preset radius β, that is, β = Gp + 2Gp;

[0050] Using the same analytical method, we can obtain the cadmium speciation distribution space Qb corresponding to each finishing step, where b refers to different finishing steps, b = 1, 2, ..., r, where r refers to the total number of finishing steps;

[0051] The spatial calibration point acquisition module analyzes and obtains the spatial calibration points corresponding to each finishing step based on the cadmium morphological characteristic points corresponding to each finishing step during the processing of multiple batches of rice. The specific method is as follows:

[0052] First, the mean values of the cadmium morphological characteristic data GAi / GAmax, GBi / GBmax and GBi / GCmax corresponding to the cadmium morphological characteristic points GHi (GAi / GAmax, GBi / GBmax, GBi / GCmax) of each batch in the target link are obtained, and then the spatial calibration points B1 (BA, BB, BC) corresponding to the target link are obtained;

[0053] By adopting the same analysis method, the spatial calibration points Bb corresponding to each finishing step can be obtained;

[0054] The reference topology coefficient acquisition module analyzes the cadmium morphological characteristic points corresponding to each finishing link and the spatial calibration points corresponding to each finishing link when processing multiple batches of rice, and obtains the reference topology coefficient corresponding to each finishing link. The specific method is as follows:

[0055] Obtain the cadmium morphological characteristic points GHi (GAi / GAmax, GBi / GBmax, GBi / GCmax) corresponding to each batch in the target link and the spatial calibration points B1 (BA, BB, BC) corresponding to the target link;

[0056] The distance Di between each cadmium morphological feature point and the spatial calibration point is calculated by the distance formula. According to the preset radius β, the cadmium morphological distribution space Q1 corresponding to the target link is divided into a spherical neighborhood with the spatial calibration point B1 as the center as the calibration point B1 neighborhood. The cadmium morphological feature points with a distance Di less than or equal to the preset radius β are determined as feature points falling into the calibration point B1 neighborhood. The number of feature points e falling into the calibration point B1 neighborhood is counted and the number e is compared with the calibration point B1 neighborhood volume V. B1 The ratio between them is taken as the neighborhood density P corresponding to the target link B1 ; Neighborhood density P B1 Reflects the degree of aggregation of cadmium species near the calibration point;

[0057] Get the neighborhood volume V of the calibration point B1 B1 The specific method is:

[0058] pass Get the neighborhood volume V of the calibration point B1 B1；

[0059] By T1 = α × P B1 +(1-α), calculate the reference topology coefficient T1 corresponding to the target link, where α is the preset weight coefficient, and the value of α is 0.5 to 0.7;

[0060] The higher the value of the benchmark topology coefficient T1, the more highly concentrated and evenly distributed the cadmium forms are near the calibration point in the target link. The lower the value of the benchmark topology coefficient T1, the more dispersed and unevenly distributed the cadmium forms are near the calibration point in the target link.

[0061] The same analysis method as that used to obtain the reference topology coefficient T1 corresponding to the target link can be used to obtain the reference topology coefficient Tb corresponding to each finishing link.

[0062] The collected data are normalized and discretized through complex analysis through the data analysis module to generate the cadmium morphological distribution space, and determine the spatial calibration points and benchmark topological coefficients.

[0063] The real-time monitoring module repeatedly acquires real-time data of various cadmium forms in rice within the monitoring link, analyzes the data to obtain multiple monitoring cadmium morphological characteristic points, analyzes whether each monitoring cadmium morphological characteristic point belongs to the cadmium morphological distribution space of the corresponding monitoring link, obtains the position qualification rate of the corresponding monitoring link, and obtains the monitoring topology coefficient based on the multiple monitoring cadmium morphological characteristic points. Based on the position qualification rate and monitoring topology coefficient of the rice within the monitoring link, it is determined whether the cadmium morphological characteristic distribution of the rice is abnormal within the corresponding monitoring link, and generates an abnormal distribution signal based on the determination result. The specific determination method is as follows:

[0064] Using sensors deployed at various stages, real-time data of cadmium content in rice was acquired multiple times during the monitoring phase, and the real-time cadmium content data were marked as Gg 实时 (GAg 实时 , GBg 实时 , GCg 实时 ); normalize the cadmium morphology characteristic points GHg by the corresponding maximum values GAmax, GBmax and GCmax of different forms of cadmium GAi, GBi and GCi in all batches, and then obtain the characteristic points of each monitored cadmium morphology GHg 实时 (GAg 实时 / GAmax,GBg 实时 / GBmax,GCg 实时 / GCmax), where g refers to different acquisition times, g = 1, 2, ..., y, y is a positive integer greater than 1;

[0065] Obtain the spatial calibration points corresponding to the real-time monitoring link and calculate the GHg of each monitored cadmium morphological characteristic point 实时 (GAg 实时 / GAmax,GBg 实时 / GBmax,GCg 实时 / GCmax) and the distance Lg between the spatial calibration point corresponding to the monitoring link, when Lg is less than or equal to the preset radius β, it is determined that the corresponding monitoring cadmium morphological characteristic point belongs to the cadmium morphological distribution space corresponding to the real-time monitoring link; when L is greater than the preset radius β, the corresponding monitoring cadmium morphological characteristic point does not belong to the cadmium morphological distribution space corresponding to the real-time monitoring link, and the ratio between the number f of monitoring cadmium morphological characteristic points belonging to the cadmium morphological distribution space corresponding to the real-time monitoring link and the number of acquisitions g is obtained as the position qualification rate JA corresponding to the real-time monitoring link;

[0066] The same calculation and analysis method as that used to obtain the benchmark topology coefficient T1 corresponding to the target link is used to calculate the monitoring topology coefficient JB corresponding to the monitoring link. The specific method is:

[0067] To monitor the cadmium form characteristic point GHg 实时As the center, draw a sphere according to the preset radius θ to obtain multiple characteristic points GHg for monitoring cadmium morphology 实时 The spherical Mg is centered, and then multiple spherical Mg are obtained, corresponding to the covering complex Vg: Vg = {(Mg,θ)|g = 1, 2, ..., y};

[0068] The union of the geometric areas covered by the complex Vg corresponding to each spherical Mg is used as the cadmium form monitoring distribution space JC corresponding to the real-time monitoring link, that is,

[0069] The preset radius θ is determined as follows;

[0070] According to GHi (GAi / GAmax, GBi / GBmax, GBi / GCmax), all monitored cadmium morphological characteristic points GHg are obtained 实时 (GAg 实时 / GAmax,GBg 实时 / GBmax,GCg 实时 / GCmax) between the standard deviation W1 and the mean W2, and the sum of the mean W2 and 2 standard deviations W1 is used as the preset radius θ, that is, θ = θ + 2W2;

[0071] The cadmium morphology monitoring distribution space JC corresponding to the real-time monitoring link is divided into a spherical neighborhood centered on the spatial calibration point corresponding to the monitoring link as the monitoring link neighborhood. The monitoring cadmium morphology feature points with a distance Lg less than or equal to the preset radius θ are determined as feature points falling within the monitoring link neighborhood. The number z of monitoring cadmium morphology feature points falling within the monitoring link neighborhood is counted, and the ratio between the number z and the volume VG within the monitoring link neighborhood is used as the monitoring density VM corresponding to the monitoring link;

[0072] By JB = α × VM + (1-α), the monitoring topology coefficient JB corresponding to the monitoring link is calculated ；

[0073] The specific method of obtaining the volume VG in the neighborhood of the monitoring link is:

[0074] pass

[0075] Obtain the absolute value of the difference JD between the reference topology coefficient and the monitoring topology coefficient corresponding to the monitoring link, calculate the sum of the products of the reciprocal of the position qualification rate JA corresponding to the real-time monitoring link and the absolute value of the difference JD and the preset value coefficients ω1 and ω2, and use them as the reasonable coefficient HL corresponding to the monitoring link. The specific values of the preset value coefficients ω1 and ω2 are formulated by relevant personnel according to actual needs, satisfying 1=ω1+ω2, ω1<ω2;

[0076] When the reasonable coefficient HL is greater than the preset value Y1, an abnormal distribution signal is generated. Otherwise, no processing is performed. The specific value of the preset value Y1 is formulated by relevant personnel according to actual needs.

[0077] It should be noted that if the position qualification rate JA is 0, then 1 / JA will be infinite, which will directly cause HL to become infinite, thus inevitably triggering an abnormal signal. When JA is 0, an abnormal distribution signal will be directly generated.

[0078] The real-time monitoring module acquires real-time data multiple times, analyzes whether the monitored cadmium morphological feature points belong to the corresponding cadmium morphological distribution space, calculates the position qualification rate and monitoring topological coefficient, and thus determines whether the cadmium morphological distribution is abnormal and generates an abnormal distribution signal;

[0079] Real-time monitoring and precise analysis of cadmium forms during rice processing have been achieved, which can timely detect abnormal cadmium content, avoid batch pollution, reduce resource waste, further ensure the stability and safety of the processing process, and improve the quality of rice products.

[0080] Example 2: As Example 2 of the present invention, please refer to Figure 2 , providing a rice deep processing monitoring method based on the Internet of Things, the method is used to implement the aforementioned disclosed rice deep processing monitoring system based on the Internet of Things, specifically comprising;

[0081] Step 1: Obtain the historical content data of each form of cadmium at each stage in the rice processing process;

[0082] Step 2: Analyze the historical content data of each form of cadmium at each link in the rice processing process to obtain the distribution space of the cadmium forms corresponding to each link. The specific method is as follows:

[0083] Select one of the multiple finishing links as the target link without replacement;

[0084] Obtain the maximum values GAmax, GBmax, and GCmax of cadmium forms GAi, GBi, and GCi in all batches, respectively, and normalize Gi(GAi, GBi, GCi) by GHi(GAi / GAmax, GBi / GBmax, GBi / GCmax);

[0085] With the cadmium morphological feature point GHi as the center, a sphere is drawn according to the preset radius β, and then multiple spheres Ai are obtained, which correspond to the covering complex Fi respectively. The union of the geometric areas covered by each sphere Ai is used as the cadmium morphological distribution space Q1 corresponding to the target link.

[0086] Using the same analytical method, we can obtain the cadmium speciation distribution space Qb corresponding to each finishing step, where b refers to different finishing steps, b = 1, 2, ..., r, where r refers to the total number of finishing steps;

[0087] The spatial calibration point acquisition module analyzes and obtains the spatial calibration points corresponding to each finishing step based on the cadmium morphological characteristic points corresponding to each finishing step during the processing of multiple batches of rice. The specific method is as follows:

[0088] First, the mean values of the cadmium morphological characteristic data GAi / GAmax, GBi / GBmax and GBi / GCmax in the cadmium morphological characteristic points GHi (GAi / GAmax, GBi / GBmax, GBi / GCmax) corresponding to each batch in the target link are obtained, and then the spatial calibration points B1 (BA, BB, BC) corresponding to the target link are obtained. The same analysis method is adopted to obtain the spatial calibration points Bb corresponding to each finishing link.

[0089] The reference topology coefficient acquisition module analyzes the cadmium morphological characteristic points corresponding to each finishing link and the spatial calibration points corresponding to each finishing link when processing multiple batches of rice, and obtains the reference topology coefficient corresponding to each finishing link. The specific method is as follows:

[0090] Obtain the cadmium morphological characteristic points GHi (GAi / GAmax, GBi / GBmax, GBi / GCmax) corresponding to each batch in the target link and the spatial calibration points B1 (BA, BB, BC) corresponding to the target link;

[0091] The distance Di between each cadmium morphological feature point and the spatial calibration point is calculated by the distance formula. According to the preset radius β, the cadmium morphological distribution space Q1 corresponding to the target link is divided into a spherical neighborhood with the spatial calibration point B1 as the center as the calibration point B1 neighborhood. The cadmium morphological feature points with a distance Di less than or equal to the preset radius β are determined as feature points falling into the calibration point B1 neighborhood. The number of feature points e falling into the calibration point B1 neighborhood is counted and the number e is compared with the calibration point B1 neighborhood volume V. B1 The ratio between them is taken as the neighborhood density P corresponding to the target link B1 ; Neighborhood density P B1 Reflects the degree of aggregation of cadmium species near the calibration point;

[0092] By T1 = α × P B1 +(1-α), calculate and obtain the reference topology coefficient T1 corresponding to the target link; use the same analysis method as that for obtaining the reference topology coefficient T1 corresponding to the target link to obtain the reference topology coefficient Tb corresponding to each finishing link;

[0093] The real-time monitoring module repeatedly acquires real-time data of various cadmium forms in rice within the monitoring link, analyzes the data to obtain multiple monitoring cadmium morphological characteristic points, analyzes whether each monitoring cadmium morphological characteristic point belongs to the cadmium morphological distribution space of the corresponding monitoring link, obtains the position qualification rate of the corresponding monitoring link, and obtains the monitoring topology coefficient based on the multiple monitoring cadmium morphological characteristic points. Based on the position qualification rate and monitoring topology coefficient of the rice within the monitoring link, it is determined whether the cadmium morphological characteristic distribution of the rice is abnormal within the corresponding monitoring link, and generates an abnormal distribution signal based on the determination result. The specific determination method is as follows:

[0094] Obtain the spatial calibration points corresponding to the real-time monitoring link and calculate the GHg of each monitored cadmium morphological characteristic point 实时 The distance Lg between each of the spatial calibration points corresponding to the monitoring link is respectively determined. When Lg is less than or equal to the preset radius β, it is determined that the corresponding monitoring cadmium morphological characteristic point belongs to the cadmium morphological distribution space corresponding to the real-time monitoring link. When L is greater than the preset radius β, the corresponding monitoring cadmium morphological characteristic point does not belong to the cadmium morphological distribution space corresponding to the real-time monitoring link. The ratio between the number f of monitoring cadmium morphological characteristic points belonging to the cadmium morphological distribution space corresponding to the real-time monitoring link and the number of acquisitions g is obtained as the position qualification rate JA corresponding to the real-time monitoring link. The same calculation and analysis method as that for obtaining the benchmark topological coefficient T1 corresponding to the target link is used to calculate the monitoring topological coefficient JB corresponding to the monitoring link. The specific method is as follows:

[0095] Obtain the absolute value of the difference JD between the reference topology coefficient and the monitoring topology coefficient corresponding to the monitoring link, calculate the sum of the products of the reciprocal of the position qualification rate JA corresponding to the real-time monitoring link and the absolute value of the difference JD and the preset value coefficients ω1 and ω2, and use them as the reasonable coefficient HL corresponding to the monitoring link. The specific values of the preset value coefficients ω1 and ω2 are formulated by relevant personnel according to actual needs, satisfying 1=ω1+ω2, ω1<ω2;

[0096] When the reasonable coefficient HL is greater than the preset value Y1, an abnormal distribution signal is generated. Otherwise, no processing is performed. The specific value of the preset value Y1 is formulated by relevant personnel according to actual needs.

[0097] It should be noted that if the position qualification rate JA is 0, then 1 / JA will be infinite, which will directly cause HL to become infinite, thus inevitably triggering an abnormal signal. When JA is 0, an abnormal distribution signal will be directly generated.

[0098] The data on the different forms of cadmium in rice were mapped to a multidimensional feature space. Based on historical health data, a "distribution space" and "spatial calibration points" were constructed to capture the distribution characteristics of cadmium forms. Furthermore, a "baseline topological coefficient" was constructed to quantify the degree of distribution aggregation and uniformity. Finally, the location qualification rate and real-time monitoring topological coefficient were calculated using real-time data and weighted and fused into a comprehensive "reasonable coefficient." This coefficient's threshold was used to determine intelligent early warnings for abnormal cadmium form distribution.

[0099] It has achieved real-time, multi-dimensional monitoring of cadmium forms in the rice processing process, and can quantitatively establish a healthy distribution benchmark based on topological characteristics. On this basis, by comprehensively considering the spatial position conformity and topological structure deviation, it can achieve intelligent judgment of cadmium form distribution anomalies, so that enterprises can carry out proactive process intervention and risk control, effectively improve the level of rice processing, and provide data support for intelligent management and continuous optimization of the production process.

[0100] Example 3: As Example 3 of the present invention, when this application is specifically implemented, compared with Example 1 and Example 2, the technical solution of this example is to combine the solutions of the above-mentioned Example 1 and Example 2 for implementation.

[0101] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters and thresholds in the formulas are set by technicians in this field according to actual conditions.

[0102] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A rice deep processing monitoring system based on the Internet of Things, characterized in that: include; The data acquisition module obtains the historical content data of each form of cadmium at each link in the rice processing process; The data analysis module analyzes the historical content data of each form of cadmium at each link in the rice processing process to obtain the distribution space of the cadmium forms corresponding to each processing link; The spatial calibration point acquisition module analyzes and obtains the spatial calibration points corresponding to each finishing step based on the cadmium morphological characteristic points corresponding to each finishing step during the processing of multiple batches of rice; The benchmark topology coefficient acquisition module analyzes the cadmium morphological characteristic points and spatial calibration points corresponding to each finishing step of multiple batches of rice to obtain the benchmark topology coefficients corresponding to each finishing step; The real-time monitoring module obtains multiple monitoring cadmium morphological characteristic points of rice in the monitoring link, analyzes whether each monitoring cadmium morphological characteristic point belongs to the cadmium morphological distribution space of the corresponding monitoring link, obtains the position qualification rate corresponding to the monitoring link, obtains the monitoring topology coefficient based on multiple monitoring cadmium morphological characteristic points, and determines the generation of abnormal distribution signals based on the position qualification rate and monitoring topology coefficient of rice in the monitoring link.

2. the rice deep processing monitoring system based on Internet of Things according to claim 1, is characterized in that, The specific method to obtain the cadmium form distribution space corresponding to each finishing step is: One of the multiple finishing links is selected as the target link without replacement; the historical content data of each form of cadmium at the target link point in the processing of multiple batches of rice are obtained, and the historical content data Gi (GAi, GBi, GCi) corresponding to each form of cadmium of rice in the target link are obtained when multiple batches are processed. After normalization, the cadmium morphological characteristic points GHi corresponding to each batch in the target link are obtained, and after discretization complex analysis of each cadmium morphological characteristic point GHi is performed, the cadmium morphological distribution space Q1 corresponding to the target link is generated, where i refers to different processing batches, i = 1, 2, ..., n, n refers to the total number of batches, and GAi, GBi and GCi refer to different forms of cadmium; By adopting the same analysis method, the cadmium form distribution space Qb corresponding to each finishing link can be obtained, where b refers to different finishing links, b = 1, 2, ..., r, where r refers to the total number of finishing links.

3. the rice intensive processing monitoring system based on Internet of Things according to claim 2, is characterized in that, The specific method of normalization is: The maximum values GAmax, GBmax and GCmax of different forms of cadmium GAi, GBi and GCi in all batches were obtained, and Gi (GAi, GBi, GCi) was normalized by GHi (GAi / GAmax, GBi / GBmax, GBi / GCmax).

4. the rice deep processing monitoring system based on Internet of Things according to claim 2, is characterized in that, The specific method of discretizing complex analysis of each cadmium morphological feature point GHi is as follows: With the cadmium morphological feature point GHi as the center, a sphere is drawn according to the preset radius β, and then multiple spheres Ai are obtained, which correspond to the covering complex Fi respectively. The union of the geometric areas covered by each sphere Ai is corresponded to the covering complex F, which is used as the cadmium morphological distribution space Q1 corresponding to the target link.

5. the rice deep processing monitoring system based on Internet of Things according to claim 4, is characterized in that, The preset radius β is determined as follows; According to GHi (GAi / GAmax, GBi / GBmax, GBi / GCmax), the mean Gp of the distances between all cadmium morphological feature points and the standard deviation of the distances between all batch feature points are obtained, and the sum of the mean Gp and 2 times the standard deviation is used as the preset radius β, that is, β = Gp + 2Gp.

6. the rice deep processing monitoring system based on Internet of Things according to claim 5, is characterized in that, The specific method of obtaining the spatial calibration points corresponding to each finishing step is: First, obtain the mean values of each cadmium morphological characteristic data GAi / GAmax, GBi / GBmax and GBi / GCmax in the cadmium morphological characteristic points GHi (GAi / GAmax, GBi / GBmax, GBi / GCmax) corresponding to each batch in the target link, and then obtain the spatial calibration point B1 (BA, BB, BC) corresponding to the target link: adopt the same analysis method to obtain the spatial calibration point Bb corresponding to each finishing link.

7. The rice deep processing monitoring system based on Internet of Things according to claim 6, is characterized in that, The corresponding benchmark topology coefficients in each finishing step are obtained as follows: Obtain the cadmium morphological characteristic points GHi (GAi / GAmax, GBi / GBmax, GBi / GCmax) corresponding to each batch in the target link and the spatial calibration points B1 (BA, BB, BC) corresponding to the target link; The distance Di between each cadmium morphological feature point and the spatial calibration point is calculated by the distance formula. According to the preset radius β, the cadmium morphological distribution space Q1 corresponding to the target link is divided into a spherical neighborhood with the spatial calibration point B1 as the center as the calibration point B1 neighborhood. The cadmium morphological feature points with a distance Di less than or equal to the preset radius β are determined as feature points falling into the calibration point B1 neighborhood. The number of feature points e falling into the calibration point B1 neighborhood is counted and the number e is compared with the calibration point B1 neighborhood volume V. B1 The ratio between them is taken as the neighborhood density P corresponding to the target link B1 ; through T1 = α × P B1 +(1-α), calculate the reference topology coefficient T1 corresponding to the target link, and α is 0.5 to 0.7; The same analysis method as that used to obtain the benchmark topology coefficient T1 corresponding to the target link can be used to obtain the benchmark topology coefficient Tb corresponding to each finishing link.

8. The rice deep processing monitoring system based on Internet of Things according to claim 7, wherein Get the neighborhood volume V of the calibration point B1 B1的具体方式 for: pass Get the neighborhood volume V of the calibration point B1 B1 .

9. The rice deep processing monitoring system based on Internet of Things according to claim 8, wherein The specific method for determining the generation of abnormal distribution signals is: The real-time data of various forms of cadmium in rice were obtained multiple times to obtain the characteristic points GHg of each monitored cadmium form. 实时 , where g refers to different acquisition times, g = 1, 2, ..., y, y is a positive integer greater than 1, obtain the spatial calibration points corresponding to the real-time monitoring link, and calculate the morphological characteristic points GHg of each monitoring cadmium 实时 The distance Lg between each of the spatial calibration points corresponding to the monitoring link is respectively determined. When Lg is less than or equal to the preset radius β, it is determined that the corresponding monitoring cadmium morphological characteristic point belongs to the cadmium morphological distribution space corresponding to the real-time monitoring link. When L is greater than the preset radius β, the corresponding monitoring cadmium morphological characteristic point does not belong to the cadmium morphological distribution space corresponding to the real-time monitoring link. The ratio between the number f of monitoring cadmium morphological characteristic points belonging to the cadmium morphological distribution space corresponding to the real-time monitoring link and the number of acquisitions g is obtained as the position qualification rate JA corresponding to the real-time monitoring link. The same calculation and analysis method as that for obtaining the benchmark topological coefficient T1 corresponding to the target link is adopted. Calculate and obtain the monitoring topology coefficient JB corresponding to the monitoring link, obtain the absolute value JD of the difference between the benchmark topology coefficient and the monitoring topology coefficient corresponding to the monitoring link, calculate the sum of the reciprocal of the position qualification rate JA corresponding to the real-time monitoring link and the product of the absolute value JD of the difference and the preset value coefficients ω1 and ω2, and use it as the reasonable coefficient HL corresponding to the monitoring link. The specific values of the preset value coefficients ω1 and ω2 are formulated by relevant personnel according to actual needs, satisfying 1=ω1+ω2, ω1<ω2. When the reasonable coefficient HL is greater than the preset value Y1, an abnormal distribution signal is generated. Otherwise, no processing is performed.

10. The rice deep processing monitoring method based on the Internet of Things is characterized in that, The method implements the Internet of Things-based rice deep processing monitoring system according to any one of claims 1 to 9, comprising: Step 1: Obtain the historical content data of each form of cadmium at each stage in the rice processing process; Step 2: Analyze the historical content data of each form of cadmium at each link in the rice processing process to obtain the distribution space of the cadmium forms corresponding to each processing link; Step 3: Obtain the spatial calibration points corresponding to each finishing step; Step 4: Obtain the corresponding benchmark topology coefficients in each finishing step; Step 5: Acquire and analyze multiple monitoring cadmium morphological characteristic points of rice in the monitoring link, obtain the position qualification rate corresponding to the monitoring link, obtain the monitoring topology coefficient, and determine the generation of abnormal distribution signals based on the position qualification rate and monitoring topology coefficient of rice in the monitoring link.

Images