Multi-region chef machine anomaly detection method and system based on target recognition

Abstract

The invention discloses a multi-region chef machine anomaly detection method and system based on target recognition, belongs to the field of target recognition, and performs dough making effect analysis based on obtained state information of flour at the beginning and dough quality under the corresponding forming degree. Abnormality analysis in the dough making process is carried out based on the dough making effect analysis result and the operation data of the chef machine, equipment operation early warning is carried out according to the abnormality analysis result in the dough making process, and the forming degree of the dough can be objectively evaluated by analyzing the state data of the dough. By means of the dough making effect analysis result and the operation data of the chef machine, abnormal conditions in the making process can be monitored in real time, the consistency and stability of final products can be ensured through strict control over the dough forming degree and quality, and the dough quality prediction accuracy is improved.

Description

Technical Field

[0001] The present invention belongs to the field of target recognition, and more specifically, to a multi-region chef machine anomaly detection method and system based on target recognition. Background Art

[0002] The existing chef machines on the market are mainly used to automate traditional pastry processes such as mixing and kneading dough, such as mixing flour, water and other raw materials, kneading dough, etc. However, in order to better optimize the dough making process and evaluate the dough forming degree, quality and production effect by analyzing the dough state data and related information in the dough making process, and then quickly monitor the abnormalities in the dough making process of the chef machine, a chef machine abnormality detection system is needed. However, when performing abnormality detection on the chef machine, the existing technology mostly only judges the failure of the equipment, and cannot objectively evaluate the dough forming degree by analyzing the dough state data, which leads to the inability to use the dough making effect analysis results and the operation data of the chef machine to monitor the abnormal conditions in the production process in real time, and thus cannot effectively complete the prediction of the dough forming degree and quality. Most of the existing technologies have the above problems;

[0003] In order to solve the problems raised by this background technology, the present application designs a multi-zone chef machine anomaly detection method and system based on target recognition. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention proposes a multi-region chef machine anomaly detection method and system based on target recognition. The present invention evaluates the degree of dough forming based on dough status data, analyzes the dough quality at the corresponding forming degree based on the dough forming degree and the dough status data, performs dough making effect analysis based on the acquired flour status information at the start and the dough quality at the corresponding forming degree, performs anomaly analysis in the dough making process based on the dough making effect analysis results and the operation data of the chef machine, and issues equipment operation warnings based on the anomaly analysis results in the dough making process. By analyzing the dough status data, the degree of dough forming can be objectively evaluated. By utilizing the dough making effect analysis results and the operation data of the chef machine, the anomalies in the production process can be monitored in real time. By predicting the dough forming degree and quality, the consistency and stability of the final product can be ensured, thereby improving the accuracy of dough quality prediction.

[0005] To achieve the above object, the present invention provides the following technical solution: a multi-zone chef machine anomaly detection method based on target recognition, which includes the following specific steps:

[0006] S1, obtaining the state data of the dough during the operation of the chef machine, obtaining the operation data of the chef machine, and obtaining the state information of the flour at the beginning;

[0007] S2. evaluating the degree of dough forming based on the dough state data, and analyzing the dough quality at the corresponding forming degree based on the dough forming degree and the dough state data;

[0008] S3, analyzing the dough making effect based on the acquired flour state information at the start and the dough quality at the corresponding forming degree;

[0009] S4, performing abnormal analysis in the dough making process based on the dough making effect analysis results and the operation data of the chef machine;

[0010] S5. Provide equipment operation warning based on abnormal analysis results during dough making.

[0011] As a preferred technical solution for the multi-region stand mixer anomaly detection method based on target recognition, the state data of the dough during the operation of the stand mixer includes parameters such as dough surface texture data and dough surface image data reflecting the degree and quality of dough forming. The operation data of the stand mixer includes parameters such as the rotation speed and vibration of the stand mixer stirring rod reflecting the quality of the stand mixer and the dough. The state information of the flour at the start includes parameters such as the particle size and color data of the flour at the start reflecting the quality state of the flour. After the data is collected, the collected data needs to be stored in each corresponding storage terminal for easy retrieval.

[0012] As a preferred technical solution of the multi-zone chef machine anomaly detection method based on target recognition, the dough forming degree evaluation based on dough state data includes the following specific contents:

[0013] The shape, color and surface texture of the dough are obtained, and the shape, color and surface texture of the dough that are historically judged to be different dough forming degrees are obtained. A convolutional neural network model whose input is the shape, color and surface texture of the dough and whose output is the dough forming degree is constructed through the shape, color and surface texture of the dough that are historically judged to be different dough forming degrees. The real-time shape, color and surface texture of the dough are imported into the constructed convolutional neural network model, and the dough forming degree at the corresponding time is output.

[0014] As a preferred technical solution of the multi-region chef machine abnormality detection method based on target recognition, the dough quality at the corresponding forming degree based on the dough forming degree and dough state data analysis includes the following specific steps:

[0015] S21, obtaining shape data and color data of the dough corresponding to the molding degree of the dough judged to be molded normally, and obtaining shape data and color data of the dough at the corresponding time, and obtaining the dough molding quality based on the maximum value of the similarities between the corresponding molding degrees of all the doughs molded normally and the doughs at the corresponding time, and the meaning of the maximum value of the similarities between the corresponding molding degrees of all the doughs molded normally and the doughs at the corresponding time is: comparing the images of the corresponding molding degrees of all the doughs molded normally with the images of the doughs at the corresponding time, respectively, obtaining the similarities between the images of the corresponding molding degrees of all the doughs molded normally and the images of the doughs at the corresponding time, forming a similarity set, and obtaining the maximum similarity in the similarity set as the dough molding quality;

[0016] S22, simultaneously acquiring color data of the dough at the corresponding time, and obtaining a dough color average value based on the inverse of the standard deviation of the pixel value data of each pixel point of the dough at the corresponding time;

[0017] S23, performing a weighted sum operation based on the dough molding quality and the dough color uniformity value to obtain the dough quality at the corresponding time.

[0018] As a preferred technical solution of the multi-region chef machine abnormality detection method based on target recognition, the dough making effect analysis based on the acquired flour state information at the start and the dough quality at the corresponding forming degree includes the following specific contents: S31, acquiring the flour state information at the start, and acquiring the flour abnormality based on the abnormality of the flour particle size and the abnormality of the color data at the start, wherein the flour abnormality can be calculated by first acquiring the difference between the average particle size of the flour and the safe particle range, and then acquiring the difference between the average pixel value data of the flour color and the safe pixel value range, and the difference is normalized and weighted summed to obtain the flour abnormality;

[0019] S32, obtaining flour shaping abnormality based on the fluctuation of flour particle size and flour moisture at the beginning, wherein the flour shaping abnormality can be calculated by: normalizing the difference between flour moisture and a safe particle range and multiplying the variance of flour particle size to obtain the flour shaping abnormality;

[0020] S33, performing weighted summation based on flour anomaly and flour forming anomaly to obtain flour forming difficulty;

[0021] S34, obtaining the dough making effect at the corresponding time by dividing the dough mass at the corresponding time by the difficulty of flour molding.

[0022] As a preferred technical solution of the multi-region chef machine anomaly detection method based on target recognition, the anomaly analysis of the dough making process based on the dough making effect analysis results and the operation data of the chef machine includes the following specific steps:

[0023] S41, obtaining operation data of the chef machine, and analyzing the abnormal operation of the chef machine based on the difference between the operation data of the chef machine and normal data and the fluctuation of the operation data;

[0024] S42. Obtain the abnormal analysis results of the chef machine operation and the dough making effect, and use the reciprocal normalized product of the chef machine operation abnormal analysis results and the dough making effect to obtain the abnormal analysis value of the dough making process. If the obtained abnormal analysis value of the dough making process is less than or equal to the set abnormal analysis threshold, it means that the dough making effect meets the requirements and no equipment operation warning is issued. If the obtained abnormal analysis value of the dough making process is greater than the set abnormal analysis threshold, it means that the dough making effect does not meet the requirements and an equipment operation warning is issued.

[0025] On the other hand, the present application proposes a multi-zone chef machine anomaly detection system based on target recognition, which is implemented based on the above method and specifically includes the following modules:

[0026] Acquisition module: used to obtain the state data of the dough during the operation of the chef machine, the operation data of the chef machine, and the state information of the flour at the beginning;

[0027] Dough quality analysis module: evaluates the degree of dough forming based on dough state data, and analyzes the dough quality at the corresponding forming degree based on the dough forming degree and dough state data;

[0028] Dough making effect analysis module: Dough making effect analysis is performed based on the acquired flour status information at the start and the dough quality at the corresponding forming degree;

[0029] Production process abnormality analysis module: Based on the dough making effect analysis results and the operation data of the chef machine, abnormality analysis of the dough making process is performed;

[0030] Equipment operation warning module: used to provide equipment operation warning based on abnormal analysis results during the dough making process.

[0031] On the other hand, the present application provides an electronic device, comprising: a processor and a memory, wherein the memory stores a computer program that can be called by the processor;

[0032] The processor executes the above-mentioned multi-zone chef machine anomaly detection method based on target recognition by calling the computer program stored in the memory.

[0033] On the other hand, the present application proposes a computer-readable storage medium storing instructions, which, when executed on a computer, enable the computer to execute the multi-zone chef machine anomaly detection method based on target recognition as described above.

[0034] Compared with the prior art, the present invention has the following beneficial effects:

[0035] The present invention evaluates the degree of dough forming based on dough state data, analyzes dough quality at a corresponding forming degree based on the dough forming degree and the dough state data, performs dough making effect analysis based on the acquired flour state information at the start and the dough quality at a corresponding forming degree, performs abnormality analysis in the dough making process based on the dough making effect analysis results and the operation data of the chef machine, and issues equipment operation early warning according to the abnormality analysis results in the dough making process. By analyzing the dough state data, the degree of dough forming can be objectively evaluated. By utilizing the dough making effect analysis results and the operation data of the chef machine, abnormal conditions in the production process can be monitored in real time. By strictly controlling the dough forming degree and quality, the consistency and stability of the final product can be ensured, thereby improving the accuracy of dough quality prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 It is a schematic diagram of the overall process of the multi-region chef machine anomaly detection method based on target recognition of the present invention;

[0037] Figure 2 It is a schematic flow chart of step S2 of the multi-zone chef machine abnormality detection method based on target recognition of the present invention;

[0038] Figure 3 It is a schematic flow chart of step S3 of the multi-zone chef machine anomaly detection method based on target recognition of the present invention;

[0039] Figure 4 Schematic diagram of the overall framework of the multi-zone chef machine anomaly detection system based on target recognition of the present invention. DETAILED DESCRIPTION

[0040] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0041] It should also be noted that, in this specification, 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 "comprise", "include" 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. In the absence of further restrictions, an element defined by the statement "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device including the element.

[0042] Here, the terms of this application are explained first: Target recognition: Recognize the state data of the dough during the operation of the chef machine;

[0043] Multiple zones: dough forming zone and chef machine operation zone;

[0044] Example 1

[0045] In order to solve the technical problems raised in the background technology, the present invention provides a preferred embodiment: Figure 1-Figure 3 As shown, the multi-region chef machine anomaly detection method based on target recognition includes the following specific steps:

[0046] S1, obtaining the state data of the dough during the operation of the chef machine, obtaining the operation data of the chef machine, and obtaining the state information of the flour at the beginning;

[0047] In a preferred embodiment, the state data of the dough during the operation of the chef machine includes parameters such as dough surface texture data and dough surface image data reflecting the degree and quality of dough forming, wherein the dough surface texture is obtained by machine vision to obtain a texture image of the dough surface, and the dough surface texture data and dough surface image data can be obtained by an image acquisition terminal after acquiring an image and then processing it with an image processing software, the operation data of the chef machine includes parameters such as the rotation speed and shaking of the stirring rod of the chef machine reflecting the quality of the noodles made by the chef machine, wherein the operation data of the chef machine is acquired by a corresponding data sensor component, and the state information of the flour at the start includes parameters such as the particle size and color data of the flour at the start reflecting the quality state of the flour, wherein the particle size and color data of the flour at the start reflecting the quality state of the flour are acquired by an image acquisition terminal or other visual terminals, and after the data is acquired, the acquired data needs to be stored in each corresponding storage terminal for easy acquisition;

[0048] S2. evaluating the degree of dough forming based on the dough state data, and analyzing the dough quality at the corresponding forming degree based on the dough forming degree and the dough state data;

[0049] In a preferred embodiment, evaluating the degree of dough forming based on dough state data includes the following specific contents:

[0050] Obtain the shape, color and surface texture of the dough, obtain the shape, color and surface texture of the dough judged to be different dough forming degrees by history, construct a convolutional neural network model whose input is the shape, color and surface texture of the dough and whose output is the dough forming degree through the shape, color and surface texture of the dough judged to be different dough forming degrees by history, import the real-time shape, color and surface texture of the dough into the constructed convolutional neural network model, and output the dough forming degree at the corresponding time;

[0051] The doughs with different dough forming degrees judged in the above history are obtained through experiments, and several groups of doughs with different dough forming degrees are obtained to manually mark the forming degrees of these doughs. The judgment of the forming degree here can be set by dividing the average value of the time from the beginning to the end of the complete forming of the dough judged to be formed normally, for example, the marking ranges from 0 to 10, that is, 0 represents unformed, 1-9 represents different forming states, and 10 represents complete forming. The collected historical data is divided into 80% training set, 10% validation set and 10% test set. The training set is used to continuously iterate the model, and the validation set is used to verify the parameters. The test set is used to test the model, and a convolutional neural network model that meets the maximum forming degree judgment accuracy is output;

[0052] At the same time, based on the dough forming degree and dough state data, the dough quality at the corresponding forming degree is analyzed, including the following specific steps:

[0053] S21, obtaining shape data and color data of the dough judged to be normally formed, and obtaining shape data and color data of the dough at the corresponding time, and obtaining dough forming quality based on the maximum value of the similarities between the corresponding forming degrees of all normally formed doughs and the dough at the corresponding time, the meaning of the maximum value of the similarities between the corresponding forming degrees of all normally formed doughs and the dough at the corresponding time is: comparing the images of the corresponding forming degrees of all normally formed doughs with the images of the dough at the corresponding time, respectively, obtaining the similarities between the images of the corresponding forming degrees of all normally formed doughs and the images of the dough at the corresponding time, forming a similarity set, obtaining the maximum similarity in the similarity set as the dough forming quality, wherein the jth normally formed dough is The similarity calculation formula between the image of the corresponding forming degree of the dough and the image of the dough at the corresponding time can be: the volume of the maximum intersection of the image of the corresponding forming degree of the j-th normally formed dough and the image contour of the dough at the corresponding time is divided by the volume of the minimum union of the image of the corresponding forming degree of the j-th normally formed dough and the image contour of the dough at the corresponding time, to obtain the similarity of the image of the corresponding forming degree of the j-th normally formed dough and the image contour of the dough at the corresponding time, and at the same time, the average image pixel value of the corresponding forming degree of the j-th normally formed dough and the average image value of the dough at the corresponding time are obtained, and the sum of the two is divided by the difference between the two and normalized to obtain the image pixel similarity, and at the same time, the image contour similarity and the image pixel similarity are weighted summed to obtain the image similarity;

[0054] S22, simultaneously acquiring color data of the dough at the corresponding time, and obtaining a dough color average value based on the inverse of the standard deviation of the pixel value data of each pixel point of the dough at the corresponding time;

[0055] S23, performing a weighted sum operation based on the dough forming quality and the dough color uniformity value to obtain the dough quality at the corresponding time;

[0056] S3, analyzing the dough making effect based on the acquired flour state information at the start and the dough quality at the corresponding forming degree;

[0057] In one of the embodiments, dough making effect analysis based on the acquired flour state information at the start and the dough quality at the corresponding forming degree includes the following specific contents: S31, acquiring flour state information at the start, acquiring flour abnormality based on the abnormality of the flour particle size and the abnormality of the color data at the start, wherein the flour abnormality can be calculated by first acquiring the difference between the average particle size of the flour and the safe particle range, then acquiring the difference between the average pixel value data of the flour color and the safe pixel value range, and obtaining the flour abnormality by weighted summation after normalization of the difference; normal flour in the present application is described as flour whose particles meet the safe particle range and whose color meets the safe color range;

[0058] S32, obtaining flour shaping abnormality based on the fluctuation of flour particle size and flour moisture at the beginning, wherein the flour shaping abnormality can be calculated by: normalizing the difference between flour moisture and a safe particle range and multiplying the variance of flour particle size to obtain the flour shaping abnormality;

[0059] S33, performing weighted summation based on flour anomaly and flour forming anomaly to obtain flour forming difficulty;

[0060] S34, obtaining the dough making effect at the corresponding time by dividing the dough quality at the corresponding time by the difficulty of flour molding, thereby avoiding the influence of the difficulty of flour molding on the dough molding effect evaluation and better evaluating the dough molding effect of the equipment, that is, if the dough is more difficult to mold and the dough quality is better, this indicates that the making effect is better, and thus the equipment is better;

[0061] S4, performing abnormal analysis in the dough making process based on the dough making effect analysis results and the operation data of the chef machine;

[0062] In one embodiment, performing abnormality analysis in the dough making process based on the dough making effect analysis result and the operation data of the chef machine includes the following specific steps:

[0063] S41, obtaining the operation data of the chef machine, and analyzing the abnormal operation of the chef machine based on the difference between the operation data of the chef machine and normal data and the fluctuation of the operation data, wherein the abnormal operation analysis formula of the chef machine can be: , where m is the number of types of operation data of the food processor, ai is the proportion coefficient of the i-th type of operation data, representing the degree of influence of the i-th type of operation data on the operation of the food processor, xi is the average value of the i-th type of operation data during the operation, for example, when stirring, the average speed of the stirring rod during operation, xim is the set value of the i-th type of operation data during the operation, for example, when running, the stirring rod needs to rotate at a speed of 300 revolutions per minute, Represents the difference between the running data of the chef machine and the normal data. is the difference proportion weight, xit is the value of the i-th operating data at time t, xi(t-1) is the value of the i-th operating data at time t-1, T is the running time of the chef machine, dt is the time integral, Represents the fluctuation of operating data, is the volatility ratio;

[0064] S42, obtaining the abnormal analysis result of the operation of the chef machine and the dough making effect, and obtaining the abnormal analysis value in the dough making process by multiplying the abnormal analysis result of the operation of the chef machine and the reciprocal normalization of the dough making effect. If the obtained abnormal analysis value in the dough making process is less than or equal to the set abnormal analysis threshold, it means that the dough making effect meets the requirements and no equipment operation warning is issued. If the obtained abnormal analysis value in the dough making process is greater than the set abnormal analysis threshold, it means that the dough making effect does not meet the requirements and an equipment operation warning is issued.

[0065] The standardization here is the process of avoiding the denominator being 0, which would make the formula meaningless. It can be done by adding a very small constant to the denominator;

[0066] For the setting parameters in the present application, the value taking method is as follows: according to the dough state data during the operation of the historical chef machine, the operation data of the chef machine and the flour state information at the start, the abnormal analysis value in the dough making process is calculated in each step of the present embodiment, and whether the dough making effect meets the requirements is judged, and the judgment result and the calculation result are fitted to obtain the setting parameter value that meets the maximum judgment accuracy;

[0067] S5. Provide equipment operation warning based on abnormal analysis results during dough making;

[0068] The advantages of this embodiment over the prior art are as follows: evaluating the degree of dough forming based on dough status data, analyzing the dough quality at the corresponding forming degree based on the dough forming degree and the dough status data, analyzing the dough making effect based on the acquired flour status information at the start and the dough quality at the corresponding forming degree, analyzing the abnormalities in the dough making process based on the dough making effect analysis results and the operating data of the chef machine, and issuing equipment operation warnings based on the abnormal analysis results in the dough making process; by analyzing the dough status data, the degree of dough forming can be objectively evaluated; by using the dough making effect analysis results and the operating data of the chef machine, the abnormal conditions in the production process can be monitored in real time; and by strictly controlling the dough forming degree and quality, the consistency and stability of the final product can be ensured, thereby improving the accuracy of dough quality prediction.

[0069] Example 2

[0070] like Figure 4 As shown, the multi-zone chef machine anomaly detection system based on target recognition is implemented based on the multi-zone chef machine anomaly detection method based on target recognition, and the acquisition module is used to obtain the state data of the dough during the operation of the chef machine, and the operation data of the chef machine, and the state information of the flour at the start;

[0071] Dough quality analysis module: evaluates the degree of dough forming based on dough state data, and analyzes the dough quality at the corresponding forming degree based on the dough forming degree and dough state data;

[0072] Dough making effect analysis module: Dough making effect analysis is performed based on the acquired flour status information at the start and the dough quality at the corresponding forming degree;

[0073] Production process abnormality analysis module: Based on the dough making effect analysis results and the operation data of the chef machine, abnormality analysis of the dough making process is performed;

[0074] Equipment operation warning module: used to issue equipment operation warning according to the abnormal analysis results in the dough making process. The specific steps of the above modules in this embodiment are specifically described in the above method embodiment, and will not be described in detail in this embodiment. Figure 4 The direction of the arrow in the figure is the direction of data transmission.

[0075] Example 3

[0076] This embodiment provides an electronic device, including: a processor and a memory, wherein the memory stores a computer program that can be called by the processor;

[0077] The processor executes the above-mentioned multi-zone chef machine anomaly detection method based on target recognition by calling the computer program stored in the memory.

[0078] The electronic device may have relatively large differences due to different configurations or performances, and may include one or more processors and one or more memories, wherein the memory stores at least one computer program, and the computer program is loaded and executed by the processor to implement the multi-zone chef machine anomaly detection method based on target recognition provided by the above method embodiment. The electronic device may also include other components for implementing the functions of the device, for example, the electronic device may also have components such as a wired or wireless network interface and an input and output interface to input and output data. This embodiment will not be described in detail here.

[0079] Example 4

[0080] This embodiment provides a computer-readable storage medium having a rewritable computer program stored thereon;

[0081] When the computer program runs on a computer device, the computer device executes the above-mentioned multi-zone chef machine anomaly detection method based on target recognition.

[0082] For example, the computer readable storage medium can be a read-only memory, a random access memory, a read-only CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.

[0083] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When a computer instruction or computer program is loaded or executed on a computer, a process or function according to an embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. Computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center through a wired network or / and a wireless network. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

Claims

1. A multi-region chef machine anomaly detection method based on target recognition, characterized in that: It includes the following specific steps: S1, obtaining the state data of the dough during the operation of the chef machine, obtaining the operation data of the chef machine, and obtaining the state information of the flour at the beginning; S2. evaluating the degree of dough forming based on the dough state data, and analyzing the dough quality at the corresponding forming degree based on the dough forming degree and the dough state data; S3, analyzing the dough making effect based on the acquired flour state information at the start and the dough quality at the corresponding forming degree; S4, performing abnormal analysis in the dough making process based on the dough making effect analysis results and the operation data of the chef machine; S5. Provide equipment operation warning based on abnormal analysis results during dough making.

2. The method for detecting abnormalities of a multi-zone chef machine based on target recognition according to claim 1, characterized in that: The method of evaluating the degree of dough forming based on dough state data includes the following specific contents: The shape, color and surface texture of the dough are obtained, and the shape, color and surface texture of the dough that are historically judged to be different dough forming degrees are obtained. A convolutional neural network model whose input is the shape, color and surface texture of the dough and whose output is the dough forming degree is constructed through the shape, color and surface texture of the dough that are historically judged to be different dough forming degrees. The real-time shape, color and surface texture of the dough are imported into the constructed convolutional neural network model, and the dough forming degree at the corresponding time is output.

3. The method for detecting abnormalities of a multi-zone chef machine based on target recognition as claimed in claim 2, characterized in that: The dough quality analysis at the corresponding forming degree based on the dough forming degree and the dough state data comprises the following specific steps: S21, obtaining shape data and color data of the dough corresponding to the molding degree of the dough judged to be molded normally, and obtaining shape data and color data of the dough at the corresponding time, and obtaining the dough molding quality based on the maximum value of the similarities between the corresponding molding degrees of all the doughs molded normally and the doughs at the corresponding time, and the meaning of the maximum value of the similarities between the corresponding molding degrees of all the doughs molded normally and the doughs at the corresponding time is: comparing the images of the corresponding molding degrees of all the doughs molded normally with the images of the doughs at the corresponding time, respectively, obtaining the similarities between the images of the corresponding molding degrees of all the doughs molded normally and the images of the doughs at the corresponding time, forming a similarity set, and obtaining the maximum similarity in the similarity set as the dough molding quality; S22, simultaneously acquiring color data of the dough at the corresponding time, and obtaining a dough color average value based on the inverse of the standard deviation of the pixel value data of each pixel point of the dough at the corresponding time; S23, performing a weighted sum operation based on the dough molding quality and the dough color uniformity value to obtain the dough quality at the corresponding time.

4. The method for detecting abnormalities of a multi-zone chef machine based on target recognition as claimed in claim 3, characterized in that: The dough making effect analysis based on the acquired flour state information at the start and the dough quality at the corresponding forming degree includes the following specific contents: S31, obtaining the state information of the flour at the start, and obtaining the flour abnormality based on the abnormality of the particle size and the abnormality of the color data of the flour at the start; S32, the fluctuation of flour particle size and flour moisture at the beginning to obtain abnormal flour forming; S33, performing weighted summation based on flour anomaly and flour forming anomaly to obtain flour forming difficulty; S34, obtaining the dough making effect at the corresponding time by dividing the dough mass at the corresponding time by the difficulty of flour molding.

5. The method for detecting abnormalities of a multi-zone chef machine based on target recognition as claimed in claim 4, characterized in that: The abnormality analysis of the dough making process based on the dough making effect analysis result and the operation data of the chef machine includes the following specific steps: S41, obtaining operation data of the chef machine, and analyzing the abnormal operation of the chef machine based on the difference between the operation data of the chef machine and normal data and the fluctuation of the operation data; S42. Obtain the abnormal analysis results of the chef machine operation and the dough making effect, and use the reciprocal normalized product of the chef machine operation abnormal analysis results and the dough making effect to obtain the abnormal analysis value of the dough making process. If the obtained abnormal analysis value of the dough making process is less than or equal to the set abnormal analysis threshold, it means that the dough making effect meets the requirements and no equipment operation warning is issued. If the obtained abnormal analysis value of the dough making process is greater than the set abnormal analysis threshold, it means that the dough making effect does not meet the requirements and an equipment operation warning is issued.

6. The method for detecting abnormalities of a multi-zone chef machine based on target recognition as claimed in claim 5, characterized in that: The state data of the dough during the operation of the chef machine includes dough surface texture data and dough surface image data reflecting parameters of the dough forming degree and forming quality. The operation data of the chef machine includes the rotation speed and vibration of the chef machine stirring rod reflecting parameters of the chef machine and dough quality. After data collection, the collected data needs to be stored in each corresponding storage terminal.

7. A multi-zone chef machine anomaly detection system based on target recognition, which is implemented based on the method according to any one of claims 1 to 6, characterized in that: It specifically includes the following modules: The multi-zone chef machine anomaly detection system based on target recognition is implemented based on the multi-zone chef machine anomaly detection method based on target recognition, and specifically includes the following modules: Acquisition module: used to obtain the state data of the dough during the operation of the chef machine, the operation data of the chef machine, and the state information of the flour at the beginning; Dough quality analysis module: evaluates the degree of dough forming based on dough state data, and analyzes the dough quality at the corresponding forming degree based on the dough forming degree and dough state data; Dough making effect analysis module: Dough making effect analysis is performed based on the acquired flour status information at the start and the dough quality at the corresponding forming degree; Production process abnormality analysis module: Based on the dough making effect analysis results and the operation data of the chef machine, abnormality analysis of the dough making process is performed; Equipment operation warning module: used to provide equipment operation warning based on abnormal analysis results during the dough making process.

8. An electronic device, comprising: A processor and a memory, wherein the memory stores a computer program that can be called by the processor; It is characterized in that the processor executes the multi-zone chef machine anomaly detection method based on target recognition as described in any one of claims 1 to 6 by calling the computer program stored in the memory.

9. A computer-readable storage medium, characterized in that: Instructions are stored, and when the instructions are executed on a computer, the computer executes the multi-zone chef machine anomaly detection method based on target recognition as described in any one of claims 1 to 6.

Images