Artificial intelligence-based intestinal soothing pet feed process monitoring system

Abstract

The present invention relates to the field of abnormal monitoring technology, and specifically to an intestinal soothing pet feed process monitoring system based on artificial intelligence, the system comprising a processor and a memory, the processor executing a computer program stored in the memory to implement the following steps: obtaining a current data change index value and a raw material input change index value, and obtaining a current abnormal index value according to the current data change index value and the raw material input change index value; obtaining a judgment index value according to a reference abnormal index value and a current abnormal index value, and obtaining a grinder operation monitoring result according to the judgment index value. In addition, in the present invention, when an abnormal operation condition occurs in a grinder of equipment for producing intestinal soothing pet feed, the present invention can accurately and timely detect it according to the judgment index value, and can timely remind the staff to check and repair the production equipment, that is, the present invention can timely and accurately detect the abnormal condition of the grinder.

Description

Technical Field

[0001] The present invention relates to the technical field of abnormal monitoring, and in particular to an intestinal soothing pet feed process monitoring system based on artificial intelligence. Background Art

[0002] Enteric soothing pet feed is a type of feed specially designed for pets. It aims to promote the health of pets' intestines and improve digestion and absorption efficiency by optimizing the formula and production process. However, when the equipment for producing enteric soothing pet feed malfunctions or operates abnormally, such as when the filter of the grinder becomes clogged or the blade becomes blunt, it will not only cause the quality of the enteric soothing pet feed produced to be poor or non-compliant, but will also affect the production efficiency of the enteric soothing pet feed. Therefore, in the production process of enteric soothing pet feed, it is very important to monitor the operating status of the equipment used in production, that is, it is very important to monitor the abnormal operating status of the grinder.

[0003] In the prior art, relevant staff generally judge whether the equipment for producing intestinal soothing pet food has abnormal operation based on their own experience. However, human subjectivity is strong, which may lead to failure to timely and accurately detect abnormal operation of the production equipment. That is, the existing detection method cannot timely and accurately detect abnormal operation of the production equipment, and thus cannot timely remind the staff to check and repair the production equipment. The equipment for producing intestinal soothing pet food or production equipment refers to a grinder. Therefore, in the production process of intestinal soothing pet food, when the production equipment has abnormal operation, how to detect it in a timely and accurate manner is an urgent problem to be solved. Summary of the invention

[0004] In order to solve the above problems, the present invention provides an intestinal soothing pet feed process monitoring system based on artificial intelligence, and the technical solutions adopted are as follows:

[0005] An embodiment of the present invention provides an artificial intelligence-based intestinal soothing pet feed process monitoring system, comprising a processor and a memory, wherein the processor executes a computer program stored in the memory to implement the following steps:

[0006] Obtaining a current current data sequence and a current raw material quantity input sequence corresponding to a current production monitoring period of the intestinal soothing pet food; the current data in the current current data sequence is the motor current of the grinder used when producing the intestinal soothing pet food, and the raw material quantity input sequence in the current raw material quantity input refers to the amount of raw materials put into the material input port of the grinder;

[0007] According to the range value of the current current data sequence and the difference between adjacent data in the current current data sequence, the current data change index value corresponding to the current production monitoring time period is obtained; according to the range value of the current raw material quantity input quantity sequence and the difference between adjacent data in the current raw material quantity input quantity sequence, the raw material quantity input quantity change index value corresponding to the current production monitoring time period is obtained;

[0008] According to the current data change index value and the raw material input quantity change index value, obtaining the current abnormality index value corresponding to the current production monitoring time period;

[0009] A reference abnormal index value is obtained, and a determination index value corresponding to the current production monitoring time period is obtained according to the reference abnormal index value and the current abnormal index value, and an operation monitoring result of the pulverizer is obtained according to the determination index value.

[0010] Beneficial effect: The present invention first obtains the current current data sequence and the current raw material input sequence corresponding to the current production monitoring time period of the intestinal soothing pet feed; then, according to the extreme value of the current current data sequence and the difference between adjacent data in the current current data sequence, the current data change index value corresponding to the current production monitoring time period is obtained; according to the extreme value of the current raw material input sequence and the difference between adjacent data in the current raw material input sequence, the raw material input change index value corresponding to the previous production monitoring time period is obtained; according to the current data change index value and the raw material input change index value, the current abnormal index value corresponding to the current production monitoring time period is obtained; then, the reference abnormal index value is obtained, and according to the reference abnormal index value and the current abnormal index value, the judgment index value corresponding to the current production monitoring time period is obtained, and finally, the operation monitoring result of the grinder is obtained according to the judgment index value. In addition, in the present invention, when the grinder of the equipment for producing intestinal soothing pet feed has an abnormal operation, the present invention can accurately and timely detect it according to the judgment index value, and can timely remind the staff to check and repair the production equipment, that is, the present embodiment can timely and accurately detect the abnormal condition of the grinder. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0012] Figure 1 The present invention is a flow chart of an intestinal soothing pet feed process monitoring method based on artificial intelligence. DETAILED DESCRIPTION

[0013] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field belong to the scope of protection of the embodiments of the present invention.

[0014] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0015] This embodiment provides an intestinal soothing pet feed process monitoring based on artificial intelligence, including a processor and a memory, wherein the processor executes a computer program stored in the memory to implement an intestinal soothing pet feed process monitoring method based on artificial intelligence, such as Figure 1 As shown, the artificial intelligence-based intestinal soothing pet feed process monitoring method includes the following steps:

[0016] like Figure 1 As shown, the artificial intelligence-based intestinal soothing pet feed process monitoring method includes the following steps:

[0017] Step S001, obtaining a current current data sequence and a current raw material quantity input quantity sequence corresponding to a current production monitoring period of intestinal soothing pet feed.

[0018] The main purpose of this embodiment is to detect in time and accurately when abnormal operation of the grinder, the main production equipment used in the production of intestinal soothing pet feed, occurs during the production process of the intestinal soothing pet feed, and to promptly remind relevant maintenance personnel to conduct inspections and repairs, so as to ensure production quality and efficiency while avoiding damage to the grinder, such as motor damage, as much as possible; and the abnormal operation in this embodiment includes but is not limited to blockage of the grinder filter and blunting of the blade, both of which affect the crushing efficiency and quality; in addition, for the convenience of analysis, this embodiment mainly monitors the grinder in any production line, that is, the intestinal soothing pet feed production monitoring time period that appears in this embodiment refers to the time period when the production line produces intestinal soothing pet feed, and the grinders that appear subsequently refer to the same grinder.

[0019] When the pulverizer is in abnormal operation, the motor current of the pulverizer is relatively unstable, that is, the motor current of the pulverizer can reflect whether the pulverizer is in abnormal operation. Therefore, in this embodiment, it is necessary to collect the current data of the pulverizer motor. In addition, in the actual production process, the different amounts of raw materials put into the material input port of the pulverizer will also cause the instability of the motor current. In order to enable the subsequent timely and accurate detection of the abnormal operation of the production equipment, this embodiment will first use the data acquisition equipment and sensors to obtain the current data and raw material input at each monitoring time in the current production monitoring time period of the intestinal soothing pet food. The current data is the motor current of the pulverizer used in the production of the intestinal soothing pet food. The raw material input at the monitoring time refers to the amount of raw materials put into the material input port of the pulverizer from the previous monitoring time of the corresponding monitoring time to the corresponding monitoring time. For example, for any monitoring time t, the raw material input at the monitoring time t refers to the amount of raw materials put into the material input port of the pulverizer in the time period from the previous monitoring time of the monitoring time t to the monitoring time t. The raw material amount refers to the weight of the raw material, and the units of all raw material amounts are consistent.

[0020] In addition, in specific applications, the implementer needs to set the current production monitoring time period and the time interval between adjacent monitoring moments according to actual conditions. For example, in this embodiment, the current production monitoring time period can be set to ten minutes, and the current production monitoring time period includes the current production moment, but does not include the time period corresponding to when the production line stops production. In this embodiment, the time interval between adjacent monitoring moments can be set to 1 second or 0.2 seconds.

[0021] Then, the time series composed of all current data obtained in the current production monitoring time period is recorded as the current current data sequence corresponding to the current production monitoring time period, and the time series composed of all raw material quantity input quantities obtained in the current production monitoring time period is recorded as the current raw material quantity input quantity sequence corresponding to the current production monitoring time period.

[0022] Therefore, this embodiment can obtain the current current data sequence and the current raw material input quantity sequence corresponding to the current production monitoring time period through the above process, and this embodiment will subsequently analyze the current current data sequence and the current raw material input quantity sequence to detect the abnormal operation condition of the crusher in a timely and accurate manner.

[0023] Step S002, according to the range value of the current current data sequence and the difference between adjacent data in the current current data sequence, obtain the current data change index value corresponding to the current production monitoring time period; according to the range value of the current raw material quantity input quantity sequence and the difference between adjacent data in the current raw material quantity input quantity sequence, obtain the raw material quantity input quantity change index value corresponding to the current production monitoring time period; according to the current data change index value and the raw material quantity input quantity change index value, obtain the current abnormality index value corresponding to the current production monitoring time period.

[0024] In the production process of enteric digestible feed, the working performance of the grinder's filter and cutter head will directly affect the production quality and efficiency. Therefore, it is necessary to monitor the working performance of the grinder's filter and cutter head, and the main monitoring in the production process is the blockage of the grinder's filter and the bluntness of the cutter head. When the grinder's filter is blocked or the cutter head is blunt, if the raw material input remains unchanged, the load on the grinder will increase, which will cause the grinder's motor current to increase. However, this situation is not absolute, because the raw material input varies, and the change in the raw material input will also affect the grinder's motor current. For example, when the input raw material amount continues to increase, the grinder's motor current will increase, and when the input raw material amount continues to decrease, the grinder's motor current will decrease. Therefore, only analyzing the grinder's motor current cannot accurately determine whether the grinder has a blocked filter or a blunt cutter head, that is, it cannot accurately determine whether the grinder has a blocked filter or a blunt cutter head. It can timely and accurately detect whether the production equipment has abnormal operation. In order to detect the abnormal operation of the production equipment in a timely and accurate manner, the present embodiment will first analyze the current current data sequence and the current raw material input sequence, and obtain the current data change index value and the raw material input change index value corresponding to the current production monitoring time period. Then, according to the current data change index value and the raw material input change index value, the current abnormal index value corresponding to the current production monitoring time period is determined. The current abnormal index value is the key to determining whether the crusher has abnormal operation, that is, combining the current data change index value and the raw material input change index value can timely and accurately determine whether the crusher has abnormal operation. In addition, when the amount of raw materials put in is stable and the filter and cutter head of the crusher work well, the load on the crusher may be relatively stable, that is, the motor current of the crusher is relatively stable.

[0025] Based on the above, this embodiment first obtains the current data change index value corresponding to the current production monitoring time period according to the extreme value of the current current data sequence and the difference between adjacent data in the current current data sequence, and the specific acquisition process of the current data change index value corresponding to the current production monitoring time period is:

[0026] First, the first difference sequence of the current current data sequence is obtained, and the mean value of the first difference sequence is recorded as the current characteristic value corresponding to the current production monitoring time period; then, the extreme difference value of the current current data sequence is obtained, and the value after multiplying the extreme difference value of the current current data sequence by the current characteristic value and adding the preset first constant is recorded as the current data change index value corresponding to the current production monitoring time period, and the bth first difference value in the first difference sequence is the absolute value of the difference between the bth current data and the b+1th current data in the current current data sequence; and the current data change index value corresponding to the current production monitoring time period is an important parameter for subsequently obtaining the current abnormal index value; and in this embodiment, the specific expression for calculating the current data change index value corresponding to the current production monitoring time period is:

[0027]

[0028] Wherein, L is the current data change index value corresponding to the current production monitoring time period, c1 is the preset first constant, and in this embodiment, the value of c1 is 0.01, and the significance of c1 here is to prevent the calculation result from being 0, L0 is the extreme value of the current current data sequence, M is the total number of data in the first difference sequence, is the mth first difference in the first difference sequence, and the extreme value is the difference between the maximum value and the minimum value in the sequence. And when The larger the value of is, the larger the value of L is. The larger the value of L is, the less similar the data in the current data sequence are, that is, the more unstable the data in the current data sequence are. The smaller the value of , the smaller the value of L is, and the smaller the value of L is, the more similar the data in the current current data sequence are, that is, the more stable the data in the current current data sequence is.

[0029] After obtaining the current data change index value corresponding to the current production monitoring time period, this embodiment will then obtain the raw material quantity input change index value corresponding to the current production monitoring time period according to the extreme value of the current raw material quantity input quantity sequence and the difference between adjacent data in the current raw material quantity input quantity sequence; and the specific acquisition process of the raw material quantity input change index value corresponding to the current production monitoring time period is:

[0030] First, the second difference sequence of the current raw material quantity input sequence is obtained, and the mean of the second difference sequence is recorded as the raw material quantity input characteristic value corresponding to the current production monitoring time period; then, the extreme difference value of the current raw material quantity input sequence is obtained, and the value after multiplying the extreme difference value of the current raw material quantity input sequence with the raw material quantity input characteristic value and adding the preset first constant is recorded as the raw material quantity input change index value corresponding to the current production monitoring time period, and the cth first difference value in the second difference sequence is the absolute value of the difference between the cth raw material quantity input and the c+1th raw material quantity input in the current raw material quantity input sequence; and the raw material quantity input change index value corresponding to the current production monitoring time period is also an important parameter for subsequently obtaining the current abnormal index value; and in this embodiment, the specific expression for calculating the raw material quantity input change index value corresponding to the current production monitoring time period is:

[0031]

[0032] Among them, G is the raw material input quantity change index value corresponding to the current production monitoring time period, G0 is the extreme value of the current current data sequence, N is the total number of data in the second difference sequence, is the nth second difference in the second difference sequence. And when The larger the value of is, the larger the value of G is. The larger the value of G is, the less similar the data in the current raw material quantity input sequence are, that is, the more unstable the data in the current raw material quantity input sequence are. On the contrary, The smaller the value of , the smaller the value of G is, and the smaller the value of G is, the more similar the data in the current raw material quantity input sequence are, that is, the more stable the data in the current raw material quantity input sequence is.

[0033] After obtaining the current data change index value and the raw material input change index value, the current abnormal index value corresponding to the current production monitoring time period is obtained according to the current data change index value and the raw material input change index value. The current abnormal index value is the key to accurately determine whether the crusher has an abnormal operation in the current production monitoring time period. Therefore, the specific process of obtaining the current abnormal index value is as follows:

[0034] First, the total amount of raw materials put into the material input port of the crusher in the current production monitoring time period is obtained, and recorded as the total raw material input corresponding to the current production monitoring time period; then the total raw material input corresponding to the current production monitoring time period is obtained by multiplying the raw material input change index value corresponding to the current production monitoring time period and then adding the value obtained by the preset first constant, and recorded as the first characterization value; then the ratio of the current data change index value corresponding to the current production monitoring time period to the first characterization value is obtained, and recorded as the current abnormal index value corresponding to the current production monitoring time period; and in this embodiment, the specific expression for calculating the current abnormal index value corresponding to the current production monitoring time period is:

[0035]

[0036] Wherein, F is the current abnormal index value corresponding to the current production monitoring time period, W is the total amount of raw materials put into the material input port of the pulverizer during the current production monitoring time period, and the preset first constant here is to prevent the denominator from being 0; Indicates the load on the crusher during the current production monitoring period.

[0037] And when The larger the value of , that is, the larger the value of F, the greater the probability that the changing relationship between the motor current and the input raw material amount in the current production monitoring time period tends to be abnormal, which further indicates that the probability of abnormal operation of the crusher in the current production monitoring time period is greater, that is, the greater the possibility that the filter of the crusher is blocked or the blade becomes blunt in the current production monitoring time period, otherwise it indicates that the probability of abnormal operation of the crusher in the current production monitoring time period is smaller; that is, based on the current abnormal index value corresponding to the current production monitoring time period, it can be more accurately distinguished whether the instability of the motor current is caused by abnormal operation of the crusher or the change in the raw material input amount, so as to accurately and timely detect whether the crusher has abnormal operation.

[0038] Therefore, this embodiment can obtain the current abnormal index value corresponding to the current production monitoring time period through the above process.

[0039] Step S003, obtaining a reference abnormal index value, obtaining a determination index value corresponding to the current production monitoring time period according to the reference abnormal index value and the current abnormal index value, and obtaining an operation monitoring result of the pulverizer according to the determination index value.

[0040] Although the current abnormal index value obtained above can reflect the probability of abnormal operation of the crusher, it is not possible to accurately determine under what circumstances the crusher has abnormal operation based only on the current abnormal index value itself. In order to achieve this purpose, this embodiment first obtains a reference abnormal index value, and the reference abnormal index value is calculated when the possibility of abnormal operation of the crusher is relatively small, that is, the reference abnormal index value is more inclined to be obtained when the crusher does not have abnormal operation. The monitoring result of the crusher will be obtained based on the reference abnormal index value later, so the acquisition process of the reference abnormal index value is as follows:

[0041] First, the historical production monitoring time period of intestinal soothing pet feed is obtained. When obtaining the historical production monitoring time period, it is also necessary to obtain the current data and raw material input quantity at each historical monitoring moment in the historical production monitoring time period of intestinal soothing pet feed; then the historical production monitoring time period is divided to obtain each historical sub-time period in the historical production monitoring time period, the current data sub-sequence corresponding to each historical sub-time period, and the corresponding raw material input quantum sequence.

[0042] In addition, the implementer needs to set the historical production monitoring time period according to the actual situation. For example, in this embodiment, the historical production monitoring time period can be set to any 24 hours in the production time period from the start of production of the production line to the current production moment, and the historical production monitoring time period does not include the time period corresponding to when the production line stops production, or the historical production monitoring time period can be set to the production time period from the start of production of the production line to the initial moment in the current production monitoring time period.

[0043] After obtaining the current data subsequence and the corresponding raw material quantity input quantum sequence corresponding to each historical sub-time period, the abnormal index value corresponding to each historical sub-time period can be calculated. Since in this embodiment, the method for obtaining the abnormal index value corresponding to the historical sub-time period is the same as the method for obtaining the current abnormal index value corresponding to the current production monitoring time period, this embodiment will not be described in detail.

[0044] Then, among the abnormal index values ​​corresponding to all historical sub-time periods, the smallest abnormal index value is selected as the reference abnormal index value.

[0045] In this embodiment, the historical production monitoring time period is divided to obtain each historical sub-time period in the historical production monitoring time period, the current data sub-sequence corresponding to each historical sub-time period, and the corresponding raw material quantity input quantum sequence as follows:

[0046] First, the time series constructed by acquiring the current data at all historical monitoring moments is recorded as the current data sequence corresponding to the historical production monitoring time period, and all current data except the current data located in the first two digits in the historical current data sequence are recorded as characteristic data.

[0047] Then, the characteristic difference between two adjacent characteristic data in the historical current data sequence is obtained. The larger the characteristic difference is, the smaller the possibility that the monitoring moments corresponding to the two characteristic data are divided into the same sub-time period is. Conversely, the smaller the characteristic difference is, the greater the possibility that the monitoring moments corresponding to the two characteristic data are divided into the same sub-time period is, that is, the greater the possibility that the two characteristic data belong to the same current change pattern is.

[0048] Next, determine whether the characteristic difference between the first characteristic data and the second characteristic data in the historical current data sequence is not greater than the preset difference threshold. If so, continue to determine whether the characteristic difference between the second characteristic data and the third characteristic data in the historical current data sequence is not greater than the preset difference threshold. If not, then the time period formed by the monitoring moments corresponding to the first four current data in the historical current data sequence is recorded as the first historical sub-time period in the historical production monitoring time period, and the first characteristic data and the second characteristic data are the third current data and the fourth current data in the historical data sequence; then continue to determine whether the characteristic difference between the third characteristic data and the fourth characteristic data in the historical current data sequence is not greater than the preset difference threshold. If so, continue to determine whether the characteristic difference between the fourth characteristic data and the fifth characteristic data in the historical current data sequence is not greater than the preset difference threshold. If not, then the time period formed by the monitoring moments corresponding to the third characteristic data and the fourth characteristic data is recorded as the second historical sub-time period in the historical production monitoring time period. For example , if the monitoring times corresponding to the 3rd characteristic data and the 4th characteristic data are 3:30:30 and 3:30:31 in the afternoon of the same day respectively, then the 2nd historical sub-time period at this time is the time period from 3:30:30 to 3:30:31; and continue to judge whether the characteristic difference between the 5th characteristic data and the 6th characteristic data in the historical current data sequence is not greater than the preset difference threshold. If so, continue to judge whether the characteristic difference between the 6th characteristic data and the 7th characteristic data in the historical current data sequence is not greater than the preset difference threshold. If not, the time period formed by the monitoring times corresponding to the 5th characteristic data and the 6th characteristic data is recorded as the 3rd historical sub-time period in the historical production monitoring time period, and continue to judge whether the characteristic difference between the 7th characteristic data and the 8th characteristic data in the historical current data sequence is not greater than the preset difference threshold, and so on, until the obtained historical sub-time period contains the monitoring time corresponding to the last current data in the historical current data sequence, and stop, and obtain all historical sub-time periods in the historical production monitoring time period by statistics.

[0049] In a specific application, the implementer needs to set the preset difference threshold value according to the actual situation and experience. For example, in this embodiment, the preset difference threshold value can be set to 0.72.

[0050] After the historical production monitoring time period is divided, the current data subsequence and raw material quantity input quantum sequence corresponding to each historical sub-time period can be determined. The specific process is: for any historical sub-time period T0 in the historical production monitoring time period, the time series sequence composed of all current data obtained in the historical sub-time period T0 is recorded as the current data subsequence corresponding to the historical sub-time period T0, and the time series sequence composed of all raw material quantity input quantities obtained in the historical sub-time period T0 is recorded as the raw material quantity input quantum sequence corresponding to the historical sub-time period T0, that is, the current data subsequence corresponding to the historical sub-time period T0 and the data in the raw material quantity input quantum sequence correspond to the collection time historical sub-time period T0.

[0051] In this embodiment, the method for obtaining the characteristic difference is: first, the neighborhood difference corresponding to each characteristic data in the historical current data sequence is obtained, and the neighborhood difference corresponding to the a-th characteristic data in the historical current data sequence is the value obtained by subtracting the a+1-th current data in the historical current data sequence from the a+2-th current data in the historical current data sequence, and the a-th characteristic data is the a+2-th current data in the historical current data sequence; for the i-th characteristic data and the i+1-th characteristic data in the historical current data sequence, the absolute value of the difference between the neighborhood difference corresponding to the i-th characteristic data and the i+1-th characteristic data is obtained, and the absolute value of the difference is normalized and recorded as the characteristic difference between the i-th characteristic data and the i+1-th characteristic data; and in this embodiment, the normalization function Norm() is used during normalization.

[0052] After obtaining the reference abnormal index value, this embodiment then obtains the determination index value corresponding to the current production monitoring time period according to the reference abnormal index value and the current abnormal index value, and then obtains the operation monitoring result of the crusher according to the determination index value. The specific process is as follows:

[0053] Obtain the normalized value of the ratio of the current abnormal index value to the reference abnormal index value, and record it as the judgment index value corresponding to the current production monitoring time period; then determine whether the judgment index value is greater than the preset judgment threshold value, if so, it is determined that the crusher has an abnormal operation in the current production monitoring time period, that is, it is determined that the filter of the crusher is blocked or the cutter head is blunt in the current production monitoring time period, then immediately remind the staff to check and repair the production equipment, that is, check and repair the filter and cutter head of the crusher, otherwise, it is determined that the crusher is operating normally in the current production monitoring time period, and production can continue, that is, it is determined that the crusher has no abnormal operation in the current production monitoring time period.

[0054] In a specific application, the implementer needs to set the preset determination threshold according to the actual situation. For example, in this embodiment, the preset determination threshold is set to 0.4.

[0055] At this point, this embodiment completes the operation monitoring of the pulverizer of the production equipment.

[0056] In summary, the present embodiment first obtains the current current data sequence and the current raw material input sequence corresponding to the current production monitoring time period of the intestinal soothing pet feed; then, according to the extreme value of the current current data sequence and the difference between adjacent data in the current current data sequence, the current data change index value corresponding to the current production monitoring time period is obtained; according to the extreme value of the current raw material input sequence and the difference between adjacent data in the current raw material input sequence, the raw material input change index value corresponding to the previous production monitoring time period is obtained; according to the current data change index value and the raw material input change index value, the current abnormal index value corresponding to the current production monitoring time period is obtained; then, the reference abnormal index value is obtained, and according to the reference abnormal index value and the current abnormal index value, the judgment index value corresponding to the current production monitoring time period is obtained, and finally, the operation monitoring result of the grinder is obtained according to the judgment index value. In this embodiment, when the grinder of the equipment for producing intestinal soothing pet feed has an abnormal operation, the present embodiment can accurately and timely detect it according to the judgment index value, and can timely remind the staff to check and repair the production equipment, that is, the present embodiment can timely and accurately detect the abnormal condition of the grinder.

[0057] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. An artificial intelligence-based intestinal soothing pet feed process monitoring system, comprising a processor and a memory, characterized in that: The processor executes the computer program stored in the memory to implement the following steps: Obtaining a current current data sequence and a current raw material quantity input sequence corresponding to a current production monitoring period of the intestinal soothing pet food; the current data in the current current data sequence is the motor current of the grinder used when producing the intestinal soothing pet food, and the raw material quantity input sequence in the current raw material quantity input refers to the amount of raw materials put into the material input port of the grinder; According to the extreme value of the current current data sequence and the difference between adjacent data in the current current data sequence, the current data change index value corresponding to the current production monitoring time period is obtained; According to the extreme value of the current raw material quantity input quantity sequence and the difference between adjacent data in the current raw material quantity input quantity sequence, the raw material quantity input quantity change index value corresponding to the current production monitoring time period is obtained; According to the current data change index value and the raw material input quantity change index value, obtaining the current abnormality index value corresponding to the current production monitoring time period; Obtaining a reference abnormal index value, obtaining a determination index value corresponding to the current production monitoring time period according to the reference abnormal index value and the current abnormal index value, and obtaining an operation monitoring result of the pulverizer according to the determination index value; The method for obtaining the current data change index value corresponding to the current production monitoring time period includes: obtaining a first difference sequence of the current current data sequence, and recording the mean of the first difference sequence as the current characteristic value corresponding to the current production monitoring time period, multiplying the extreme difference value of the current current data sequence by the current characteristic value and adding a preset first constant, and recording the value as the current data change index value corresponding to the current production monitoring time period, and the bth first difference value in the first difference sequence is the absolute value of the difference between the bth current data and the b+1th current data in the current current data sequence; The specific expression for calculating the current data change index value corresponding to the current production monitoring time period is: ； Wherein, L is the current data change index value corresponding to the current production monitoring time period, c1 is the preset first constant, L0 is the extreme difference value of the current current data sequence, M is the total number of data in the first difference sequence, is the mth first difference in the first difference sequence; The method for obtaining the raw material quantity input quantity change index value corresponding to the current production monitoring time period includes: obtaining a second difference sequence of the current raw material quantity input quantity sequence, and recording the mean of the second difference sequence as the raw material quantity input quantity characteristic value corresponding to the current production monitoring time period, multiplying the extreme difference value of the current raw material quantity input quantity sequence by the raw material quantity input quantity characteristic value and adding a preset first constant, and recording the value as the raw material quantity input quantity change index value corresponding to the current production monitoring time period, and the cth second difference value in the second difference sequence is the absolute value of the difference between the cth raw material quantity input quantity and the c+1th raw material quantity input quantity in the current raw material quantity input quantity sequence; The specific expression for calculating the raw material input change index value corresponding to the current production monitoring time period is: ； Among them, G is the raw material input quantity change index value corresponding to the current production monitoring time period, G0 is the extreme value of the current current data sequence, N is the total number of data in the second difference sequence, is the nth second difference in the second difference sequence; The method for obtaining the current abnormal index value corresponding to the current production monitoring time period includes: obtaining the total amount of raw materials put into the material input port of the pulverizer during the current production monitoring time period, and recording it as the total raw material input amount corresponding to the current production monitoring time period, multiplying the total raw material input amount by the raw material input amount change index value, and then adding the value obtained by multiplying the total raw material input amount by the raw material input amount change index value and then adding the value obtained by multiplying the total raw material input amount by the preset first constant, and recording it as the first characterization value; recording the ratio of the current data change index value to the first characterization value as the current abnormal index value corresponding to the current production monitoring time period; The specific expression for calculating the current abnormal index value corresponding to the current production monitoring time period is: ； Among them, F is the current abnormal index value corresponding to the current production monitoring time period, and W is the total amount of raw materials put into the material input port of the crusher during the current production monitoring time period; The method for obtaining the determination index value includes: recording a normalized value of the ratio of the current abnormal index value to the reference abnormal index value as the determination index value corresponding to the current production monitoring time period.

2. The artificial intelligence-based intestinal soothing pet feed process monitoring system according to claim 1, characterized in that: The method for obtaining the operation monitoring result of the pulverizer according to the determination index value comprises: It is determined whether the determination index value is greater than a preset determination threshold value. If so, it is determined that the crusher has an abnormal operation in the current production monitoring time period. Otherwise, it is determined that the crusher operates normally in the current production monitoring time period.

3. The artificial intelligence-based intestinal soothing pet feed process monitoring system according to claim 1, characterized in that: The method for obtaining the reference abnormality index value includes: Obtaining a historical production monitoring time period of intestinal soothing pet feed, and dividing the historical production monitoring time period to obtain each historical sub-time period in the historical production monitoring time period; Acquire the abnormal index value corresponding to the historical sub-time period, wherein the method for acquiring the abnormal index value corresponding to the historical sub-time period is the same as the method for acquiring the current abnormal index value corresponding to the current production monitoring time period; Among the abnormal index values ​​corresponding to all historical sub-time periods, the smallest abnormal index value is selected as the reference abnormal index value.

4. The artificial intelligence-based intestinal soothing pet feed process monitoring system according to claim 3, characterized in that: The method for obtaining each historical sub-time period in the historical production monitoring time period includes: Acquire a historical current data sequence corresponding to the historical production monitoring time period, and record all current data except the first two bits of current data in the historical current data sequence as characteristic data; Determine whether the characteristic difference between the first characteristic data and the second characteristic data in the historical current data sequence is not greater than the preset difference threshold value. If so, continue to determine whether the characteristic difference between the second characteristic data and the third characteristic data in the historical current data sequence is not greater than the preset difference threshold value. If not, record the monitoring time period corresponding to the first four current data in the historical current data sequence as the first historical sub-time period in the historical production monitoring time period; and continue to determine whether the characteristic difference between the third characteristic data and the fourth characteristic data in the historical current data sequence is not greater than the preset difference threshold value. If so, continue to determine whether the characteristic difference between the fourth characteristic data and the fifth characteristic data in the historical current data sequence is not greater than the preset difference threshold value. If not, record the monitoring time period corresponding to the third characteristic data and the fourth characteristic data as the historical production monitoring time period. The second historical sub-time period in the production monitoring time period; and continue to judge whether the characteristic difference between the 5th characteristic data and the 6th characteristic data in the historical current data sequence is not greater than the preset difference threshold; if so, continue to judge whether the characteristic difference between the 6th characteristic data and the 7th characteristic data in the historical current data sequence is not greater than the preset difference threshold; if not, the monitoring time period corresponding to the 5th characteristic data and the 6th characteristic data is recorded as the 3rd historical sub-time period in the historical production monitoring time period, and continue to judge whether the characteristic difference between the 7th characteristic data and the 8th characteristic data in the historical current data sequence is not greater than the preset difference threshold, and so on, until the obtained historical sub-time period contains the monitoring time corresponding to the last current data in the historical current data sequence, and stop, and obtain all historical sub-time periods in the historical production monitoring time period by statistics.

5. The artificial intelligence-based intestinal soothing pet feed process monitoring system according to claim 4, characterized in that: The method for obtaining the characteristic difference includes: Obtaining a neighborhood difference value corresponding to each characteristic data in the historical current data sequence, wherein the neighborhood difference value corresponding to the a-th characteristic data in the historical current data sequence is a value obtained by subtracting the a+1-th current data in the current data sequence from the a+2-th current data in the historical current data sequence; For the i-th characteristic data and the i+1-th characteristic data in the historical current data sequence, the normalized value of the absolute value of the difference between the neighborhood differences corresponding to the i-th characteristic data and the i+1-th characteristic data is recorded as the characteristic difference between the i-th characteristic data and the i+1-th characteristic data.

Images