A full-process intelligent management system and method for soy products based on big data

Abstract

The present invention discloses a full-process intelligent management system and method for bean products based on big data, and belongs to the field of data analysis technology. The present invention establishes a processing time curve chart of an automated machine to calculate the grinding quantity threshold; monitors the grinding process in the processing of bean products, analyzes the number of soybeans that exceed the grinding quantity threshold, establishes a grinding efficiency curve chart of the automated machine, and establishes a formula for predicting the time that affects the grinding efficiency; monitors the entire process of bean product processing, analyzes the number of soybeans consumed in production, the number of finished products obtained by processing and production, and the time spent on processing and production, establishes a processing production efficiency curve chart, and establishes a formula for predicting the time that affects the processing production efficiency; manages the automated machine according to the real-time number of processed soybeans. Clean the filter of the automated machine in advance to avoid affecting production.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis, and in particular to a full-process intelligent management system and method for soy products based on big data. Background Art

[0002] With the popularization of intelligent assembly lines, more and more soy product processing plants are using intelligent assembly lines for processing, especially when grinding soybeans. Through intelligent assembly lines, soybeans are ground for the first time, soy milk and bean dregs are separated, and soy milk is added to water for a second grinding through automated machines. Intelligent assembly lines can improve the grinding efficiency of soybeans, but because the automated machines are used to separate soy milk and bean dregs, the filter of the automated machines may be blocked after running for a period of time. However, since the soy product processing plants need to grind too many soybeans a day, the decrease in grinding efficiency may not be discovered in time, or it may be discovered too late, resulting in too long a time spent on cleaning the filter, affecting production efficiency. Therefore, it is necessary to intelligently manage the automated machines in the soy product grinding process, predict the time when problems occur in the automated machines, and clean the filters of the automated machines in advance to avoid affecting production. Summary of the invention

[0003] The purpose of the present invention is to provide a full-process intelligent management system and method for soy products based on big data to solve the problems raised in the above-mentioned background technology.

[0004] In order to solve the above technical problems, the present invention provides the following technical solutions: a full-process intelligent management system and method for soy products based on big data, the method comprising:

[0005] Step S100: establishing a processing time curve of the automated machine according to the amount of soybeans to be processed and the time it takes for the automated machine to work in the grinding process, and calculating a grinding quantity threshold according to the processing time curve;

[0006] Step S200: monitoring the grinding process in the bean product processing according to the grinding quantity threshold, analyzing the number of soybeans exceeding the grinding quantity threshold, establishing a grinding efficiency curve of the automated machine, and establishing a formula for predicting the time duration affecting the grinding efficiency according to the slope change of the grinding efficiency curve;

[0007] Step S300: monitoring the whole process of bean product processing, analyzing the amount of soybeans consumed in the whole process of bean product processing, the amount of finished products obtained by processing, and the time spent on processing, establishing a processing efficiency curve, analyzing the maximum value of the processing efficiency curve, and establishing a formula for predicting the time that affects the processing efficiency;

[0008] Step S400: Based on the real-time quantity of processed soybeans, when the grinding quantity threshold is exceeded, the real-time quantity is respectively input into the formula for predicting the time duration affecting grinding efficiency and the formula for predicting the time duration affecting processing production efficiency, and the timing starts from the time when the automated machine starts grinding. When the predicted time duration from when the automated machine starts working to when the efficiency of the automated machine decreases is exceeded, a reminder is given to clean the filter. When the predicted time duration from when processing production starts to when the efficiency of processing production decreases is exceeded, the automated machine is stopped and the filter is forced to be cleaned.

[0009] Furthermore, step S100 includes:

[0010] Step S101: Collect the number of soybeans processed in the grinding process during the soy product processing, and obtain the number of soybeans processed for the i-th time as S i , the automated machine used in the grinding process of soy product processing, the processing quantity is S i The time spent on grinding soybeans is collected to obtain the time spent on the automated machine, and a processing time curve is established based on the amount of soybeans processed in the grinding process and the time spent on the automated machine in each bean product processing;

[0011] Step S102: According to the processing time curve, calculate the slope of the nth segment data as K n , according to the formula: , where y n and n-1 They are represented as the nth and n-1th values ​​of the y-axis of the processing time curve, respectively. n and X n-1 They are represented as the nth and n-1th values ​​of the X-axis of the machining time graph, respectively;

[0012] Step S103: Calculate the mth slope change value Q according to the slope of each segment of data m , according to the formula: , where K n-1 It is expressed as the slope of the n-1th segment of data. The slope change values ​​are arranged in ascending order to obtain the maximum slope change value. The slope corresponding to the maximum slope change value is collected, and the number of soybeans corresponding to the slope is collected and compared. The minimum number of soybeans is used as the grinding quantity threshold.

[0013] Because in the whole process of bean product processing, the processing machine needs to be cleaned after a complete processing; the main problem affecting the grinding process in the whole process of bean product processing is that the soybean dregs after soybean grinding cause clogging of the filter screen of the automatic machine, resulting in a decrease in grinding efficiency; considering the above, if the number of soybeans to be ground in the grinding stage is too small, the generated bean dregs may not cause too much impact on the filter screen of the automatic machine, and cleaning the machine after processing will not affect the next use, so it is necessary to study the issue of how much soybeans will affect the working efficiency of the automatic machine;

[0014] Based on this problem, the time spent on grinding different quantities of soybeans was collected, with the X-axis representing the number of soybeans and the Y-axis representing the time spent on grinding. A processing time curve was established, and the slope of each segment was collected. However, the grinding quantity threshold cannot be determined based on the slope, because as the quantity increases, the time spent will also increase, which will affect the accuracy of the grinding quantity threshold. Therefore, the slope change value of each segment is calculated based on the slope, so that the grinding quantity threshold obtained will be more accurate.

[0015] Further, step S200 includes:

[0016] Step S201: Retrieve the grinding quantity threshold, collect the number of processed soybeans that exceeds the grinding quantity threshold, monitor the grinding process in the soy product processing, and collect the number of processed soybeans S r , every other cycle, the number of soybeans consumed by grinding is collected, and the number of soybeans consumed by grinding for the jth time is S jr , collect the number of semi-finished products generated by grinding, and get the number of semi-finished products generated by grinding in the jth collection as C jr , collect the time spent on grinding, and get the time spent on grinding for the jth time as T jr , the grinding efficiency of the grinding process at the jth collection is calculated to be W jr , according to the formula: , according to the grinding efficiency and collection time of each grinding process, a grinding efficiency curve is established;

[0017] Step S202: According to the grinding efficiency curve, the slope of the grinding efficiency curve is collected, and the time taken for the slope sign to change twice is collected, and the collected time is added to obtain the number of processed soybeans S. r When the automatic machine starts working, the total time of the interval from when the automatic machine starts working to when the efficiency of the automatic machine decreases during the grinding process is t jr , according to the formula: , where a and b represent the weights of predicting the time length that affects grinding efficiency. The total time length from when the automated machine starts working to when the efficiency of the automated machine decreases in the grinding process corresponding to the number of different processed soybeans is trained to obtain the weights of predicting the time length that affects grinding efficiency, and the formula for predicting the time length that affects grinding efficiency is established. , where t y It is expressed as the predicted duration of the interval from when the automated machine starts working to when the efficiency of the automated machine decreases during the grinding process, and S is expressed as the amount of processed soybeans.

[0018] Because it was mentioned before that the grinding efficiency will be affected only when the number of soybeans exceeds the grinding number threshold, it is necessary to analyze the number of soybeans that exceed the grinding number threshold, so that the results of the analysis will be more accurate;

[0019] In the process of automatic machine grinding, the grinding efficiency of the grinding process may fluctuate at the beginning of grinding due to the shape of the soybeans or probabilistic problems. It is not because the filter of the automatic machine is blocked that the grinding efficiency decreases, because the efficiency is definitely the highest at the beginning, and the filter blockage will definitely decrease. However, the initial fluctuation is definitely downward and then upward. Therefore, the total time interval when the efficiency of the automatic machine decreases can be calculated based on the time it takes for the slope sign to change twice.

[0020] Because the number of soybeans is different, the total duration of the interval from when the automated machine starts working to when the efficiency of the automated machine drops in the grinding process will also be different. Based on the two, a formula for predicting the time that affects the grinding efficiency is established. This will play a role in predicting the duration of the interval from when the automated machine starts working to when the efficiency of the automated machine drops in the grinding process based on the number of soybeans.

[0021] Furthermore, step S300 includes:

[0022] Step S301: Retrieve the quantity S of processed soybeans r , monitor the whole process of bean product processing, collect the amount of soybean consumed in processing and production every other cycle, and get the amount of soybean consumed in the e-th collection and processing production as S er , collect the number of finished products obtained from processing and production, and get the number of finished products obtained from the e-th collection and processing production as C er , collect the time spent on processing and production, and get the time spent on processing and production for the eth time as T er , the processing efficiency of the whole process of bean product processing is calculated to be W at the e-th collection. er , according to the formula: , according to the processing efficiency and collection time of the whole process of bean product processing each time, a processing efficiency curve is established;

[0023] Step S302: According to the processing production efficiency curve, the time corresponding to the maximum value in the processing production efficiency curve is collected to obtain the processed soybean quantity S r When the processing efficiency decreases, the time interval from the beginning of processing to the decline of processing efficiency is t er , according to the formula: , where c and d represent the weights of the predicted time affecting the processing efficiency. The training is carried out based on the predicted time interval from the beginning of processing to the decrease of processing efficiency corresponding to the number of different processed soybeans and the number of different processed soybeans. The weights of the predicted time affecting the processing efficiency are obtained, and the formula for predicting the time affecting the processing efficiency is established. , where t v It is expressed as the predicted duration of the interval from the start of processing production to the decline in processing production efficiency, and S is the number of processed soybeans.

[0024] Because in the whole process of bean product processing, the most critical step is to grind soybeans, because the speed of soybean grinding determines whether the subsequent processes can proceed, so the soy product processing efficiency is mostly caused by the decline in the efficiency of the grinding process. However, the decline in the efficiency of the grinding process cannot directly affect the soy product processing efficiency, because the semi-finished products such as soy milk obtained in the grinding process cannot be consumed in one go in the subsequent processes, so the grinding efficiency will decline. However, there are still semi-finished products obtained from the previous grinding, which will not affect the soy product processing efficiency. However, the decline in the soy product processing efficiency will affect the delivery of orders, so it is necessary to analyze the time that affects the processing efficiency;

[0025] Because the amount of soybeans is different, the interval length from the start of processing and production to the time when processing production efficiency decreases will also be different. Based on the two, a formula for predicting the time that affects processing production efficiency is established. This will play a role in predicting the length of the interval from the start of processing and production to the time when processing production efficiency decreases based on the amount of soybeans.

[0026] Furthermore, step S400 includes:

[0027] Step S401: Each time the whole process of bean product processing is executed, the number of processed soybeans is collected in real time. When the number of processed soybeans exceeds the grinding number threshold, the number of processed soybeans is input into the formula for predicting the time length affecting the grinding efficiency, and the predicted time length t1 of the interval from when the automated machine starts to work to when the automated machine efficiency decreases is calculated. The number of processed soybeans is input into the formula for predicting the time length affecting the processing production efficiency, and the predicted time length t2 of the interval from when the processing production starts to when the processing production efficiency decreases is calculated.

[0028] Step S402: start timing from the time when the automated machine starts grinding. When the grinding time reaches t1, an alarm is sounded to the automated machine to remind the staff to clean the filter of the automated machine. When the grinding time reaches t2, the automated machine stops working, forcing the staff to clean the filter of the automated machine.

[0029] According to the amount of soybeans to be processed, the two formulas are inputted for calculation respectively to obtain the predicted duration of the interval from when the automated machine starts working to when the efficiency of the automated machine decreases and the predicted duration of the interval from when the processing production starts to when the processing production efficiency decreases. When the grinding time reaches the predicted duration of the interval from when the processing production starts to when the processing production efficiency decreases, it indicates that the filter of the automated machine may have been or is about to be clogged. At this time, the staff is reminded to clean it to avoid a decrease in processing production efficiency due to a decrease in grinding efficiency.

[0030] When the grinding time reaches the predicted duration from the start of processing to the decline in processing efficiency, it means that the processing efficiency may have declined or is about to decline. The most likely reason may be the decline in the efficiency of the grinding process. Therefore, the automated machine must be stopped and the staff must be forced to clean the automated machine filter to avoid a continuous decline in processing efficiency, which will affect order delivery.

[0031] In order to better implement the above method, a full-process intelligent management system for soy products based on big data is also proposed. The system includes a grinding quantity threshold module, a grinding efficiency module, a processing production efficiency module and a real-time management module;

[0032] Grinding quantity threshold module: according to the number of processed soybeans and the time spent by the automated machine in the grinding process, a processing time curve of the automated machine is established, and the grinding quantity threshold is calculated based on the processing time curve;

[0033] Grinding efficiency module: monitors the grinding process in bean product processing according to the grinding quantity threshold, analyzes the number of soybeans that exceed the grinding quantity threshold, establishes a grinding efficiency curve for the automated machine, and establishes a formula for predicting the time that affects the grinding efficiency according to the slope change of the grinding efficiency curve;

[0034] Processing efficiency module: monitor the whole process of soy product processing, analyze the amount of soybeans consumed in the whole process of soy product processing, the number of finished products obtained by processing and the time spent on processing, establish a processing efficiency curve, analyze the maximum value of the processing efficiency curve, and establish a formula to predict the time that affects the processing efficiency;

[0035] Real-time management module: According to the real-time quantity of processed soybeans, when the grinding quantity threshold is exceeded, the real-time quantity is respectively input into the formula for predicting the time affecting the grinding efficiency and the formula for predicting the time affecting the processing production efficiency. The timing starts from the time when the automated machine starts grinding. When the predicted time interval from the start of the automated machine to the decrease in the efficiency of the automated machine is exceeded, a reminder is given to clean the filter. When the predicted time interval from the start of processing and production to the decrease in processing production efficiency is exceeded, the automated machine is stopped and the filter is forced to be cleaned.

[0036] Further, the grinding quantity threshold module includes a processing time curve chart unit and a grinding quantity threshold calculation unit;

[0037] Processing time curve chart unit: collect the number of soybeans processed in the grinding process in the bean product processing to obtain the number of soybeans processed each time, collect the time spent by the automated machine to process different numbers of soybeans, and obtain the time spent by the automated machine. According to the number of soybeans processed in the grinding process in each bean product processing and the time spent by the automated machine, a processing time curve chart is established;

[0038] Calculate grinding quantity threshold value unit: According to the processing time curve, calculate the slope value, calculate the slope value, obtain the slope change value, and obtain the grinding quantity threshold value according to the maximum value of the slope change value.

[0039] Further, the grinding efficiency module includes a grinding efficiency curve chart unit and a calculation and prediction formula unit for the time period affecting the grinding efficiency;

[0040] Grinding efficiency curve unit: collects the number of processed soybeans that exceed the grinding quantity threshold, monitors the grinding process in the processing of soybean products, calculates the number of soybeans consumed by grinding, the number of semi-finished products generated by grinding, and the time spent, and obtains a grinding efficiency curve;

[0041] Calculation and prediction of the time formula that affects grinding efficiency: According to the grinding efficiency curve, the slope of the grinding efficiency curve is collected, and according to the change in the slope, the total time interval from the start of the automated machine to the decrease in the efficiency of the automated machine in the grinding process is calculated, and according to the total time interval between the different quantities of processed soybeans and the corresponding decrease in the efficiency of the automated machine, a formula for predicting the time interval that affects grinding efficiency is established.

[0042] Furthermore, the processing production efficiency module includes a processing production efficiency curve chart unit and a calculation and prediction unit for a formula for the duration affecting the processing production efficiency;

[0043] Processing production efficiency curve unit: collect the number of processed soybeans that exceed the grinding quantity threshold, monitor the entire process of soybean product processing, calculate the number of soybeans consumed in processing production, the number of semi-finished products obtained in processing production, and the time spent to obtain a processing production efficiency curve;

[0044] Calculation and prediction of the time formula that affects the processing production efficiency: According to the processing production efficiency curve, the time corresponding to the maximum value of the processing production efficiency curve is collected to obtain the interval from the start of processing production to the decrease in processing production efficiency. According to the interval between different quantities of processed soybeans and the corresponding decrease in processing production efficiency, a formula for predicting the time that affects the processing production efficiency is established.

[0045] Furthermore, the real-time management module includes a duration calculation unit and a judgment reminder unit;

[0046] The time calculation unit: each time the whole process of bean product processing is executed, the number of processed soybeans is collected in real time. When the number of processed soybeans exceeds the grinding number threshold, the number of processed soybeans is input into the formula for predicting the time affecting grinding efficiency and the formula for predicting the time affecting processing production efficiency, respectively, to calculate the predicted time of the interval from when the automated machine starts working to when the efficiency of the automated machine decreases and the predicted time of the interval from when processing and production starts to when the processing production efficiency decreases;

[0047] Judgment reminder unit: start timing when the automated machine is grinding, and when the grinding time reaches the predicted time interval from when the automated machine starts working to when the efficiency of the automated machine decreases, remind the staff to clean the filter of the automated machine; when the grinding time reaches the predicted time interval from when the processing and production starts to when the processing and production efficiency decreases, the automated machine stops working and forces the staff to clean the filter of the automated machine.

[0048] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: the calculation of the grinding quantity threshold is a standard for the subsequent establishment of a prediction formula and data collection. With the data collected by this standard, the accuracy of establishing the prediction formula will be greatly improved; according to the time taken for the slope sign to change in the grinding efficiency curve, the total time interval when the efficiency of the automated machine decreases in the grinding process is obtained, so that the collection avoids the fluctuation of the grinding efficiency when the automated machine starts grinding. According to this fluctuation, the total time interval when the efficiency of the automated machine decreases is determined to be inaccurate, so the collected data is more accurate through this method; the processing efficiency is analyzed because the grinding efficiency decreases, but there are very few soybeans left that need to be ground, which will not affect the processing efficiency; according to the time calculated by the two formulas, a reminder is first given to the staff, and the staff judges whether the filter can be ground before the time interval when the processing efficiency decreases based on the staff's experience. The forced shutdown is to prevent the staff from making mistakes in judgment; therefore, the filter of the automated machine is cleaned in time to avoid affecting production. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0050] Figure 1 It is a flow chart of a method for intelligent management of the whole process of bean products based on big data according to the present invention;

[0051] Figure 2 It is a structural schematic diagram of a full-process intelligent management system for soy products based on big data in the present invention; DETAILED DESCRIPTION

[0052] See also Figure 1-Figure 2 The present invention provides a technical solution: a full-process intelligent management method for soy products based on big data, the method comprising:

[0053] Step S100: establishing a processing time curve of the automated machine according to the amount of soybeans to be processed and the time it takes for the automated machine to work in the grinding process, and calculating a grinding quantity threshold according to the processing time curve;

[0054] Wherein, step S100 includes:

[0055] Step S101: Collect the number of soybeans processed in the grinding process during the soy product processing, and obtain the number of soybeans processed for the i-th time as S i , the automated machine used in the grinding process of soy product processing, the processing quantity is S iThe time spent on grinding soybeans is collected to obtain the time spent on the automated machine, and a processing time curve is established based on the amount of soybeans processed in the grinding process and the time spent on the automated machine in each bean product processing;

[0056] Step S102: According to the processing time curve, calculate the slope of the nth segment data as K n , according to the formula: , where y n and n-1 They are represented as the nth and n-1th values ​​of the y-axis of the processing time curve, respectively. n and X n-1 They are represented as the nth and n-1th values ​​of the X-axis of the machining time graph, respectively;

[0057] Step S103: Calculate the mth slope change value Q according to the slope of each segment of data m , according to the formula: , where K n-1 It is expressed as the slope of the n-1th segment of data. The slope change values ​​are arranged in ascending order to obtain the maximum slope change value. The slope corresponding to the maximum slope change value is collected, and the number of soybeans corresponding to the slope is collected and compared. The minimum number of soybeans is used as the grinding quantity threshold.

[0058] Step S200: monitoring the grinding process in the bean product processing according to the grinding quantity threshold, analyzing the number of soybeans exceeding the grinding quantity threshold, establishing a grinding efficiency curve of the automated machine, and establishing a formula for predicting the time duration affecting the grinding efficiency according to the slope change of the grinding efficiency curve;

[0059] Wherein, step S200 includes:

[0060] Step S201: Retrieve the grinding quantity threshold, collect the number of processed soybeans that exceeds the grinding quantity threshold, monitor the grinding process in the soy product processing, and collect the number of processed soybeans S r , every other cycle, the number of soybeans consumed by grinding is collected, and the number of soybeans consumed by grinding for the jth time is S jr , collect the number of semi-finished products generated by grinding, and get the number of semi-finished products generated by grinding in the jth collection as C jr , collect the time spent on grinding, and get the time spent on grinding for the jth time as T jr , the grinding efficiency of the grinding process at the jth collection is calculated to be W jr , according to the formula: , according to the grinding efficiency and collection time of each grinding process, a grinding efficiency curve is established;

[0061] Step S202: According to the grinding efficiency curve, the slope of the grinding efficiency curve is collected, and the time taken for the slope sign to change twice is collected, and the collected time is added to obtain the number of processed soybeans S. r When the automatic machine starts working, the total time of the interval from when the automatic machine starts working to when the efficiency of the automatic machine decreases during the grinding process is t jr , according to the formula: , where a and b represent the weights of predicting the time length that affects grinding efficiency. The total time length from when the automated machine starts working to when the efficiency of the automated machine decreases in the grinding process corresponding to the number of different processed soybeans is trained to obtain the weights of predicting the time length that affects grinding efficiency, and the formula for predicting the time length that affects grinding efficiency is established. , where t y It is expressed as the predicted duration of the interval from when the automated machine starts working to when the efficiency of the automated machine decreases during the grinding process, and S is expressed as the amount of processed soybeans.

[0062] Step S300: monitoring the whole process of bean product processing, analyzing the amount of soybeans consumed in the whole process of bean product processing, the amount of finished products obtained by processing, and the time spent on processing, establishing a processing efficiency curve, analyzing the maximum value of the processing efficiency curve, and establishing a formula for predicting the time that affects the processing efficiency;

[0063] Wherein, step S300 includes:

[0064] Step S301: Retrieve the quantity S of processed soybeans r , monitor the whole process of bean product processing, collect the amount of soybean consumed in processing and production every other cycle, and get the amount of soybean consumed in the e-th collection and processing production as S er , collect the number of finished products obtained from processing and production, and get the number of finished products obtained from the e-th collection and processing production as C er , collect the time spent on processing and production, and get the time spent on processing and production for the eth time as T er , the processing efficiency of the whole process of bean product processing is calculated to be W at the e-th collection. er , according to the formula: , according to the processing efficiency and collection time of the whole process of bean product processing each time, a processing efficiency curve is established;

[0065] Step S302: According to the processing production efficiency curve, the time corresponding to the maximum value in the processing production efficiency curve is collected to obtain the processed soybean quantity S rWhen the processing efficiency decreases, the time interval from the beginning of processing to the decline of processing efficiency is t er , according to the formula: , where c and d represent the weights of the predicted time affecting the processing efficiency. The training is carried out based on the predicted time interval from the beginning of processing to the decrease of processing efficiency corresponding to the number of different processed soybeans and the number of different processed soybeans. The weights of the predicted time affecting the processing efficiency are obtained, and the formula for predicting the time affecting the processing efficiency is established. , where t v It is expressed as the predicted duration of the interval from the start of processing production to the decline in processing production efficiency, and S is the number of processed soybeans.

[0066] Step S400: According to the real-time quantity of processed soybeans, when the grinding quantity threshold is exceeded, the real-time quantity is input into the formula for predicting the time length affecting grinding efficiency and the formula for predicting the time length affecting processing production efficiency, respectively. Timing starts from the time when the automated machine starts grinding. When the predicted time length of the interval from when the automated machine starts working to when the efficiency of the automated machine decreases is exceeded, a reminder is given to clean the filter. When the predicted time length of the interval from when the processing production starts to when the processing production efficiency decreases is exceeded, the automated machine is stopped and the filter is forced to be cleaned.

[0067] Wherein, step S400 includes:

[0068] Step S401: Each time the whole process of bean product processing is executed, the number of processed soybeans is collected in real time. When the number of processed soybeans exceeds the grinding number threshold, the number of processed soybeans is input into the formula for predicting the time length affecting the grinding efficiency, and the predicted time length t1 of the interval from when the automated machine starts to work to when the automated machine efficiency decreases is calculated. The number of processed soybeans is input into the formula for predicting the time length affecting the processing production efficiency, and the predicted time length t2 of the interval from when the processing production starts to when the processing production efficiency decreases is calculated.

[0069] Step S402: start timing from the time when the automated machine starts grinding. When the grinding time reaches t1, an alarm is sounded to the automated machine to remind the staff to clean the filter of the automated machine. When the grinding time reaches t2, the automated machine stops working, forcing the staff to clean the filter of the automated machine.

[0070] In order to better implement the above method, a full-process intelligent management system for soy products based on big data is also proposed. The system includes a grinding quantity threshold module, a grinding efficiency module, a processing production efficiency module and a real-time management module;

[0071] Grinding quantity threshold module: according to the number of processed soybeans and the time spent by the automated machine in the grinding process, a processing time curve of the automated machine is established, and the grinding quantity threshold is calculated based on the processing time curve;

[0072] Wherein, the grinding quantity threshold module includes a processing time curve chart unit and a grinding quantity threshold calculation unit;

[0073] Processing time curve chart unit: collect the number of soybeans processed in the grinding process in the bean product processing to obtain the number of soybeans processed each time, collect the time spent by the automated machine to process different numbers of soybeans, and obtain the time spent by the automated machine. According to the number of soybeans processed in the grinding process in each bean product processing and the time spent by the automated machine, a processing time curve chart is established;

[0074] Calculate grinding quantity threshold value unit: According to the processing time curve, calculate the slope value, calculate the slope value, obtain the slope change value, and obtain the grinding quantity threshold value according to the maximum value of the slope change value.

[0075] Grinding efficiency module: monitors the grinding process in bean product processing according to the grinding quantity threshold, analyzes the number of soybeans that exceed the grinding quantity threshold, establishes a grinding efficiency curve for the automated machine, and establishes a formula for predicting the time that affects the grinding efficiency according to the slope change of the grinding efficiency curve;

[0076] Among them, the grinding efficiency module includes a grinding efficiency curve chart unit and a calculation and prediction formula unit for the time affecting the grinding efficiency;

[0077] Grinding efficiency curve unit: collects the number of processed soybeans that exceed the grinding quantity threshold, monitors the grinding process in the processing of soybean products, calculates the number of soybeans consumed by grinding, the number of semi-finished products generated by grinding, and the time spent, and obtains a grinding efficiency curve;

[0078] Calculation and prediction of the time formula that affects grinding efficiency: According to the grinding efficiency curve, the slope of the grinding efficiency curve is collected, and according to the change in the slope, the total time interval from the start of the automated machine to the decrease in the efficiency of the automated machine in the grinding process is calculated, and according to the total time interval between the different quantities of processed soybeans and the corresponding decrease in the efficiency of the automated machine, a formula for predicting the time interval that affects grinding efficiency is established.

[0079] Processing efficiency module: monitor the whole process of soy product processing, analyze the amount of soybeans consumed in the whole process of soy product processing, the number of finished products obtained by processing and the time spent on processing, establish a processing efficiency curve, analyze the maximum value of the processing efficiency curve, and establish a formula to predict the time that affects the processing efficiency;

[0080] Among them, the processing production efficiency module includes a processing production efficiency curve chart unit and a calculation and prediction unit for the time formula affecting the processing production efficiency;

[0081] Processing production efficiency curve unit: collect the number of processed soybeans that exceed the grinding quantity threshold, monitor the entire process of soybean product processing, calculate the number of soybeans consumed in processing production, the number of semi-finished products obtained in processing production, and the time spent to obtain a processing production efficiency curve;

[0082] Calculation and prediction of the time formula that affects the processing production efficiency: According to the processing production efficiency curve, the time corresponding to the maximum value of the processing production efficiency curve is collected to obtain the interval from the start of processing production to the decrease in processing production efficiency. According to the interval between different quantities of processed soybeans and the corresponding decrease in processing production efficiency, a formula for predicting the time that affects the processing production efficiency is established.

[0083] Real-time management module: According to the real-time quantity of processed soybeans, when the grinding quantity threshold is exceeded, the real-time quantity is respectively input into the formula for predicting the time affecting the grinding efficiency and the formula for predicting the time affecting the processing production efficiency. The timing starts from the time when the automated machine starts grinding. When the predicted time interval from the start of the automated machine to the decrease in the efficiency of the automated machine is exceeded, a reminder is given to clean the filter. When the predicted time interval from the start of processing and production to the decrease in processing production efficiency is exceeded, the automated machine is stopped and the filter is forced to be cleaned.

[0084] Among them, the real-time management module includes a duration calculation unit and a judgment reminder unit;

[0085] Duration calculation unit: Each time the whole process of soy product processing is executed, the number of processed soybeans is collected in real time. When the number of processed soybeans exceeds the grinding quantity threshold, the number of processed soybeans is input into the formula for predicting the time affecting grinding efficiency and the formula for predicting the time affecting processing production efficiency, respectively, to calculate the predicted duration of the interval from when the automated machine starts working to when the automated machine efficiency decreases and the predicted duration of the interval from when processing and production starts to when the processing production efficiency decreases;

[0086] Judgment reminder unit: start timing when the automated machine is grinding, and when the grinding time reaches the predicted time interval from when the automated machine starts working to when the efficiency of the automated machine decreases, remind the staff to clean the filter of the automated machine; when the grinding time reaches the predicted time interval from when the processing and production starts to when the processing and production efficiency decreases, the automated machine stops working and forces the staff to clean the filter of the automated machine.

[0087] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0088] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for intelligent management of the whole process of soy products based on big data, characterized in that: Methods include: Step S100: establishing a processing time curve of the automated machine according to the amount of soybeans to be processed and the time it takes for the automated machine to work in the grinding process, and calculating a grinding quantity threshold according to the processing time curve; Step S200: monitoring the grinding process in the bean product processing according to the grinding quantity threshold, analyzing the number of soybeans exceeding the grinding quantity threshold, establishing a grinding efficiency curve of the automated machine, and evaluating and calculating the predicted duration of the interval from when the automated machine starts working to when the efficiency of the automated machine decreases during the grinding process according to the slope change of the grinding efficiency curve; The step S200 includes: Step S201: Retrieve the grinding quantity threshold, collect the number of processed soybeans that exceeds the grinding quantity threshold, monitor the grinding process in the soy product processing, and collect the number of processed soybeans S r , every other cycle, the number of soybeans consumed by grinding is collected, and the number of soybeans consumed by grinding for the jth time is S jr , collect the number of semi-finished products generated by grinding, and get the number of semi-finished products generated by grinding in the jth collection as C jr , collect the time spent on grinding, and get the time spent on grinding for the jth time as T jr , the grinding efficiency of the grinding process at the jth collection is calculated to be W jr , according to the formula: , according to the grinding efficiency and collection time of each grinding process, a grinding efficiency curve is established; Step S202: According to the grinding efficiency curve, the slope of the grinding efficiency curve is collected, and the time taken for the slope sign to change twice is collected, and the collected time is added to obtain the number of processed soybeans S. r When the automatic machine starts working, the total time of the interval from when the automatic machine starts working to when the efficiency of the automatic machine decreases during the grinding process is t jr , according to the formula: , where a and b represent the weights of predicting the time length that affects grinding efficiency. The total time length from when the automated machine starts working to when the efficiency of the automated machine decreases in the grinding process corresponding to the number of different processed soybeans is trained to obtain the weights of predicting the time length that affects grinding efficiency, and the formula for predicting the time length that affects grinding efficiency is established. , where t y It is represented as the predicted duration of the interval from when the automated machine starts working to when the efficiency of the automated machine decreases in the grinding process, and S represents the amount of processed soybeans; Step S300: monitoring the whole process of bean product processing, analyzing the amount of soybeans consumed in the whole process of bean product processing, the amount of finished products obtained by processing, and the time spent on processing, establishing a processing efficiency curve, analyzing the maximum value of the processing efficiency curve, and evaluating and calculating the predicted time of the interval from the beginning of processing to the time when the processing efficiency decreases; The step S300 includes: Step S301: Retrieve the quantity S of processed soybeans r , monitor the whole process of bean product processing, collect the amount of soybean consumed in processing and production every other cycle, and get the amount of soybean consumed in the e-th collection and processing production as S er , collect the number of finished products obtained from processing and production, and get the number of finished products obtained from the e-th collection and processing production as C er , collect the time spent on processing and production, and get the time spent on processing and production for the eth time as T er , the processing efficiency of the whole process of bean product processing is calculated to be W at the e-th collection. er , according to the formula: , according to the processing efficiency and collection time of the whole process of bean product processing each time, a processing efficiency curve is established; Step S302: According to the processing production efficiency curve, the time corresponding to the maximum value in the processing production efficiency curve is collected to obtain the processed soybean quantity S r When the processing efficiency decreases, the time interval from the beginning of processing to the decline of processing efficiency is t er , according to the formula: , where c and d represent the weights of the predicted time affecting the processing efficiency. The training is carried out based on the predicted time interval from the beginning of processing to the decrease of processing efficiency corresponding to the number of different processed soybeans and the number of different processed soybeans. The weights of the predicted time affecting the processing efficiency are obtained, and the formula for predicting the time affecting the processing efficiency is established. , where t v It is represented as the predicted duration of the interval from the start of processing production to the decline of processing production efficiency, and S is represented as the number of processed soybeans; Step S400: Based on the real-time quantity of processed soybeans, when the grinding quantity threshold is exceeded, the real-time quantity is respectively input into the formula for predicting the time duration affecting grinding efficiency and the formula for predicting the time duration affecting processing production efficiency, and the timing starts from the time when the automated machine starts grinding. When the predicted time duration from when the automated machine starts working to when the efficiency of the automated machine decreases is exceeded, a reminder is given to clean the filter. When the predicted time duration from when processing production starts to when the efficiency of processing production decreases is exceeded, the automated machine is stopped and the filter is forced to be cleaned.

2. The method for intelligent management of the whole process of soy products based on big data according to claim 1, characterized in that: The process of calculating the grinding quantity threshold in step S100 includes the following steps: Step S101: Collect the number of soybeans processed in the grinding process during the soy product processing, and obtain the number of soybeans processed for the i-th time as S i , the automated machine used in the grinding process of soy product processing, the processing quantity is S i The time spent on grinding soybeans is collected to obtain the time spent on the automated machine, and a processing time curve is established based on the amount of soybeans processed in the grinding process and the time spent on the automated machine in each bean product processing; Step S102: According to the processing time curve, calculate the slope of the nth segment data as K n , according to the formula: , where y n and n-1 They are represented as the nth and n-1th values ​​of the y-axis of the processing time curve, respectively. n and X n-1 They are represented as the nth and n-1th values ​​of the X-axis of the machining time graph, respectively; Step S103: Calculate the mth slope change value Q according to the slope of each segment of data m , according to the formula: , where K n-1 It is expressed as the slope of the n-1th segment of data. The slope change values ​​are arranged in ascending order to obtain the maximum slope change value. The slope corresponding to the maximum slope change value is collected, and the number of soybeans corresponding to the slope is collected and compared. The minimum number of soybeans is used as the grinding quantity threshold.

3. The method for intelligent management of the whole process of soy products based on big data according to claim 1, characterized in that: The step S400 includes the following steps: Step S401: Each time the whole process of bean product processing is executed, the number of processed soybeans is collected in real time. When the number of processed soybeans exceeds the grinding number threshold, the number of processed soybeans is input into the formula for predicting the time length affecting the grinding efficiency, and the predicted time length t1 of the interval from when the automated machine starts to work to when the automated machine efficiency decreases is calculated. The number of processed soybeans is input into the formula for predicting the time length affecting the processing production efficiency, and the predicted time length t2 of the interval from when the processing production starts to when the processing production efficiency decreases is calculated. Step S402: start timing from the time when the automated machine starts grinding. When the grinding time reaches t1, an alarm is sounded to the automated machine to remind the staff to clean the filter of the automated machine. When the grinding time reaches t2, the automated machine stops working, forcing the staff to clean the filter of the automated machine.

4. A full-process intelligent management system for bean products based on big data, used to implement the full-process intelligent management method for bean products based on big data as described in any one of claims 1 to 3, characterized in that: Grinding quantity threshold module, grinding efficiency module, processing production efficiency module and real-time management module; The grinding quantity threshold module: establishes a processing time curve of the automated machine according to the quantity of the processed soybeans and the time it takes for the automated machine to work in the grinding process, and calculates the grinding quantity threshold according to the processing time curve; The grinding efficiency module: monitors the grinding process in the bean product processing according to the grinding quantity threshold, analyzes the number of soybeans exceeding the grinding quantity threshold, establishes a grinding efficiency curve of the automated machine, and establishes a formula for predicting the time that affects the grinding efficiency according to the slope change of the grinding efficiency curve; The processing efficiency module: monitors the entire process of bean product processing, analyzes the amount of soybeans consumed in the entire process of bean product processing, the amount of finished products obtained by processing, and the time spent on processing, establishes a processing efficiency curve, analyzes the maximum value of the processing efficiency curve, and establishes a formula for predicting the time that affects the processing efficiency; The real-time management module: based on the real-time quantity of processed soybeans, when the grinding quantity threshold is exceeded, the real-time quantity is input into the formula for predicting the time affecting the grinding efficiency and the formula for predicting the time affecting the processing production efficiency, respectively, and the timing starts from the time when the automated machine starts grinding. When the predicted time interval from the start of the automated machine to the decrease in the efficiency of the automated machine is exceeded, a reminder is given to clean the filter. When the predicted time interval from the start of processing and production to the decrease in processing and production efficiency is exceeded, the automated machine is stopped and the filter is forced to be cleaned.

5. According to claim 4, a big data-based intelligent management system for the entire process of soy products is characterized in that: The grinding quantity threshold module includes a processing time curve chart unit and a grinding quantity threshold calculation unit; The processing time curve chart unit: collects the number of soybeans processed in the grinding process in the bean product processing to obtain the number of soybeans processed each time, collects the time spent by the automated machine to process different numbers of soybeans to obtain the time spent by the automated machine, and establishes a processing time curve chart according to the number of soybeans processed in the grinding process in each bean product processing and the time spent by the automated machine; The grinding quantity threshold value calculating unit calculates the slope value according to the processing time curve, calculates the slope value to obtain the slope change value, and obtains the grinding quantity threshold value according to the maximum value of the slope change value.

6. The intelligent management system for the whole process of bean products based on big data according to claim 4 is characterized in that: The grinding efficiency module includes a grinding efficiency curve chart unit and a calculation and prediction formula unit for the time period affecting the grinding efficiency; The grinding efficiency curve unit collects the number of processed soybeans exceeding the grinding quantity threshold, monitors the grinding process in the bean product processing, and calculates the grinding efficiency curve according to the number of soybeans consumed by grinding, the number of semi-finished products generated by grinding, and the time spent; The calculation and prediction formula unit for the time affecting grinding efficiency is as follows: based on the grinding efficiency curve, the slope of the grinding efficiency curve is collected, and based on the change in the slope, the total time interval from the start of the automated machine to the decrease in the efficiency of the automated machine in the grinding process is calculated, and based on the total time interval between different quantities of processed soybeans and the corresponding decrease in the efficiency of the automated machine, a formula for predicting the time affecting grinding efficiency is established.

7. The intelligent management system for the whole process of soy products based on big data according to claim 4 is characterized in that: The processing production efficiency module includes a processing production efficiency curve chart unit and a calculation and prediction unit for a formula that affects the processing production efficiency; The processing production efficiency curve unit collects the number of processed soybeans that exceeds the grinding quantity threshold, monitors the entire process of soybean product processing, and calculates the processing production efficiency curve according to the number of soybeans consumed in the processing production, the number of semi-finished products obtained in the processing production, and the time spent; The calculation and prediction formula unit for the time period affecting the processing production efficiency is as follows: based on the processing production efficiency curve, the time corresponding to the maximum value of the processing production efficiency curve is collected to obtain the time interval from the start of processing production to the time when the processing production efficiency decreases, and based on the time interval between different quantities of processed soybeans and the corresponding decrease in processing production efficiency, a formula for predicting the time period affecting the processing production efficiency is established.

8. The intelligent management system for the whole process of bean products based on big data according to claim 4 is characterized in that: The real-time management module includes a duration calculation unit and a judgment and reminder unit; The time calculation unit: each time the whole process of bean product processing is executed, the number of processed soybeans is collected in real time. When the number of processed soybeans exceeds the grinding number threshold, the number of processed soybeans is input into the formula for predicting the time affecting grinding efficiency and the formula for predicting the time affecting processing production efficiency, respectively, to calculate the predicted time of the interval from when the automated machine starts working to when the efficiency of the automated machine decreases and the predicted time of the interval from when processing and production starts to when the processing production efficiency decreases; The judgment and reminder unit starts timing when the automated machine is grinding, and when the grinding time reaches the predicted time interval from the start of the automated machine to the decrease in efficiency, the staff is reminded to clean the filter of the automated machine; when the grinding time reaches the predicted time interval from the start of processing and production to the decrease in processing and production efficiency, the automated machine stops working and forces the staff to clean the filter of the automated machine.

Images