Fault prediction method and system for pine nut full-automatic circulation processing equipment

Abstract

The invention provides a fault prediction method and system for pine nut full-automatic circulation processing equipment, and relates to the technical field of data analysis, and the method comprises the steps: collecting pine nut images in a plurality of screening regions through a camera; obtaining an actual quantity set, and calculating to obtain an actual weight set; performing consistency analysis on the actual weight set by taking the standard weight threshold value as a reference to obtain a plurality of screening consistency coefficients; continuously monitoring to obtain a plurality of screening consistency coefficient sequences, and carrying out mean value calculation, fluctuation analysis and trend fitting; and if any consistency coefficient mean value, fluctuation coefficient or trend coefficient does not meet a preset coefficient threshold, performing fault early warning. Through the method and the device, the technical problem of poor equipment fault prediction accuracy caused by complex and diversified fault types and difficulty in comprehensive fault identification in the prior art can be solved, whether the equipment has a fault or not is predicted according to the screening result of the pine nuts, the fault state of the equipment is comprehensively detected, and the equipment fault prediction accuracy is improved.

Description

Technical Field

[0001] This application relates to the technical field of data analysis, and particularly to a fault prediction method and system for a fully automatic transfer and processing equipment of pine nuts. Background Art

[0002] The fully automatic transfer and processing equipment of pine nuts is a device used to realize the full-process automation of pine nuts, including raw material feeding, sorting, shelling, kernel-shell separation, air separation, screening, weighing, packaging, etc. It is used for nut processing to improve processing efficiency, ensure product quality, and reduce labor costs. The existing methods can predict and judge the operating state of the equipment to a certain extent through trend analysis based on sensor data such as vibration, temperature, and current, or through analysis based on equipment operation logs and historical fault data. However, the equipment structure is complex, and the types of faults that may occur are often complex and diverse. The existing fault prediction methods cannot comprehensively identify all types of faults, especially the initial and minor abnormalities are often difficult to detect.

[0003] In summary, in the prior art, there are technical problems that due to the complex and diverse types of faults, it is difficult to identify all faults comprehensively, especially the initial and minor abnormalities are often difficult to detect, resulting in poor accuracy of equipment fault prediction. Summary of the Invention

[0004] The purpose of this application is to provide a fault prediction method and system for a fully automatic transfer and processing equipment of pine nuts, so as to solve the technical problems in the prior art that due to the complex and diverse types of faults, it is difficult to identify all faults comprehensively, especially the initial and minor abnormalities are often difficult to detect, resulting in poor accuracy of equipment fault prediction.

[0005] To achieve the above purpose, this application provides a fault prediction method and system for a fully automatic transfer and processing equipment of pine nuts.

[0006] In a first aspect, the present application provides a fault prediction method for a fully automatic transfer and processing device for pine nuts. The fault prediction method for the fully automatic transfer and processing device for pine nuts is implemented through a fault prediction system for the fully automatic transfer and processing device for pine nuts. Among them, the fault prediction method for the fully automatic transfer and processing device for pine nuts includes: collecting pine nut images in a plurality of screening areas through a camera to obtain a pine nut image set. Among them, the pine nut specifications in each screening area are different, and the pine nut specifications include a standard weight threshold; performing pine nut feature recognition based on the pine nut image set to obtain an actual quantity set, and calculating to obtain an actual weight set; taking the standard weight threshold as a benchmark, performing consistency analysis on the actual weight set to obtain a plurality of screening consistency coefficients for a plurality of screening areas; continuously monitoring to obtain a plurality of screening consistency coefficient sequences within a preset time range, and performing mean calculation, fluctuation analysis, and trend fitting to obtain a plurality of consistency coefficient means, a plurality of fluctuation coefficients, and a plurality of trend coefficients; if any one of the consistency coefficient means, fluctuation coefficients, or trend coefficients does not meet the preset coefficient threshold, a fault warning is given to the pine nut screening device.

[0007] Optionally, according to the historical screening records of the same type of pine nut screening device, collect a sample pine nut image set, and obtain the actual number of pine nuts in different sample pine nut images as the sample pine nut quantity to obtain a sample quantity set; use the sample pine nut images as inputs and the sample quantity as supervision, and use the sample pine nut image set and the sample quantity set to train and test a convolutional neural network until convergence to obtain a pine nut quantity recognition plug-in; use the pine nut quantity recognition plug-in to perform pine nut feature recognition on each of the plurality of pine nut images in the pine nut image set, and output an actual quantity set.

[0008] Optionally, weigh the total weight of pine nuts in a plurality of screening areas to construct a total pine nut weight set; perform mapping calculation based on the total pine nut weight set and the actual quantity set, and output an actual weight set, where the actual weight is the average weight of a single pine nut.

[0009] Optionally, randomly select the first standard weight threshold of the first screening area and obtain the first actual weight; take the median of the first standard weight threshold as the first standard weight mean, calculate the deviation ratio between the first standard weight mean and the first actual weight, and set the reciprocal of the deviation ratio as the first screening consistency coefficient, and add it to the plurality of screening consistency coefficients.

[0010] Optionally, within a preset time range, continuously perform image collection and consistency analysis to obtain a plurality of screening consistency coefficient sequences; respectively perform mean calculation on the plurality of screening consistency coefficient sequences to obtain a plurality of consistency coefficient means; perform fluctuation analysis and trend fitting respectively based on the plurality of screening consistency coefficient sequences, and output a plurality of fluctuation coefficients and a plurality of trend coefficients.

[0011] Optionally, calculate the standard deviation of each of the several screening consistency coefficient sequences to obtain several consistency coefficient standard deviations; calculate several fluctuation coefficients based on the several consistency coefficient standard deviations and several consistency coefficient means, where the fluctuation coefficient is the ratio of the consistency coefficient standard deviation to the consistency coefficient mean.

[0012] Optionally, use the monitoring time node as the X-axis and the screening consistency coefficient as the Y-axis to construct a two-dimensional coordinate system; within the two-dimensional coordinate system, distribute and curve fit the several screening consistency coefficient sequences to obtain several trend curves; identify the several trend curves to obtain several trend coefficients, where the trend coefficient is the overall rising or falling ratio.

[0013] Optionally, the preset coefficient thresholds include a consistency coefficient threshold, a fluctuation coefficient threshold, and a trend decline ratio threshold, where the preset coefficient thresholds are set based on the pine nut specifications.

[0014] Optionally, if the mean value of the consistency coefficient in any screening area is less than the consistency coefficient threshold and / or the fluctuation coefficient is greater than the fluctuation coefficient threshold and / or the decline ratio of the trend coefficient is greater than the trend decline ratio threshold, a fault warning is given to the pine nut screening device.

[0015] In a second aspect, the present application also provides a fault prediction system for a fully automatic transfer and processing equipment for pine nuts, which is used to execute a fault prediction method for a fully automatic transfer and processing equipment for pine nuts as described in the first aspect. The fault prediction system for a fully automatic transfer and processing equipment for pine nuts includes: an image acquisition module, which is used to collect pine nut images in several screening areas through a camera to obtain a pine nut image set, where the pine nut specifications in each screening area are different, and the pine nut specifications include a standard weight threshold; a weight calculation module, which is used to identify pine nut features based on the pine nut image set to obtain an actual quantity set and calculate an actual weight set; a consistency analysis module, which is used to perform consistency analysis on the actual weight set based on the standard weight threshold to obtain several screening consistency coefficients for several screening areas; a dynamic monitoring and analysis module, which is used to continuously monitor and obtain several screening consistency coefficient sequences within a preset time range, and perform mean value calculation, fluctuation analysis, and trend fitting to obtain several consistency coefficient means, several fluctuation coefficients, and several trend coefficients; a threshold judgment module, which is used to give a fault warning to the pine nut screening device if any of the consistency coefficient means, fluctuation coefficients, or trend coefficients does not meet the preset coefficient thresholds.

[0016] One or more technical solutions provided in the present application have at least the following technical effects or advantages: Collect pine nut images within several screening areas through a camera to obtain a pine nut image set. Among them, the pine nut specifications in each screening area are different, and the pine nut specifications include a standard weight threshold. Identify pine nut features based on the pine nut image set to obtain an actual quantity set, and calculate an actual weight set. Based on the standard weight threshold, perform consistency analysis on the actual weight set to obtain several screening consistency coefficients for several screening areas. Continuously monitor and obtain several screening consistency coefficient sequences within a preset time range, and perform mean calculation, fluctuation analysis, and trend fitting to obtain several consistency coefficient means, several fluctuation coefficients, and several trend coefficients. If any consistency coefficient mean, fluctuation coefficient, or trend coefficient does not meet the preset coefficient threshold, a fault warning is issued for the pine nut screening device. That is to say, by analyzing the weight fluctuations of pine nuts during the pine nut screening process, comprehensively analyze the operating status of the equipment, monitor the consistency coefficients of multiple screening areas, and detect slight but continuous deviations in advance during the screening processes of different areas and different specifications, capture complex hidden faults such as equipment degradation, aging, and calibration imbalance, and issue an early warning to accurately judge the abnormalities in the initial stage of equipment operation, improving the accuracy and efficiency of fault prediction for the fully automatic transfer and processing equipment of pine nuts.

[0017] The above description is only an overview of the technical solution of this application. In order to be able to understand the technical means of this application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features, and advantages of this application more obvious and understandable, the following specifically gives the specific implementation manners of this application. It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of this application, nor is it used to limit the scope of this application. Other features of this application will become easily understood through the following description. Brief Description of the Drawings

[0018] In order to more clearly illustrate the technical solutions in this application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings described below are only exemplary, and for those of ordinary skill in the art, other drawings can be obtained according to the provided drawings without creative efforts.

[0019] Figure 1 It is a flowchart of a fault prediction method for a fully automatic transfer and processing equipment of pine nuts according to this application; Figure 2 It is a structural diagram of a fault prediction system for a fully automatic transfer and processing equipment of pine nuts according to this application.

[0020] Explanation of the reference numerals: Image acquisition module 11, weight calculation module 12, consistency analysis module 13, dynamic monitoring and analysis module 14, threshold judgment module 15. Detailed implementation mode

[0021] By providing a fault prediction method and system for a fully automatic transfer and processing equipment of pine nuts, the present application solves the technical problem in the prior art that it is difficult to identify all faults due to the complex and diverse fault types, especially the initial and minor abnormalities are often difficult to be detected, resulting in poor accuracy of equipment fault prediction. By predicting whether a fault occurs from the screening results of pine nuts, comprehensively analyzing the operating state of the equipment, collecting and analyzing the images of pine nuts in each screening area and of each specification, monitoring the consistency coefficient of multiple screening areas, and detecting slight but continuous deviations in advance during the screening processes of different areas and different specifications, capturing complex latent faults such as equipment degradation, aging, and calibration imbalance, and giving early warnings, accurately judging the abnormalities in the initial stage of equipment operation, the accuracy and efficiency of fault prediction for the fully automatic transfer and processing equipment of pine nuts are improved.

[0022] Next, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. It should be understood that the present application is not limited by the exemplary embodiments described herein. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the scope of protection of the present application. Additionally, it should be noted that for the convenience of description, only the parts related to the present application are shown in the accompanying drawings rather than all of them.

[0023] Embodiment 1. Please refer to the attached Figure 1 , the present application provides a fault prediction method for a fully automatic transfer and processing equipment of pine nuts. Among them, the fault prediction method for a fully automatic transfer and processing equipment of pine nuts is applied to a fault prediction system for a fully automatic transfer and processing equipment of pine nuts. The fault prediction method for a fully automatic transfer and processing equipment of pine nuts specifically includes the following steps: S100: Collect the images of pine nuts in several screening areas through a camera to obtain a set of pine nut images. Among them, the pine nut specifications in each screening area are different, and the pine nut specifications include the standard weight threshold.

[0024] Specifically, industrial cameras installed above each screening area are used to collect real-time images of pine nuts in that area, generating a set of pine nut images for different areas, which together constitute a complete set of pine nut images, including images of several types of pine nuts in several screening areas. Since the specifications of the pine nuts screened in each screening area are different, the characteristics of the pine nuts corresponding to each image set (such as weight and size) are also different. The screening areas are independent screening units preset for different specifications of pine nuts, and each screening area is specially configured according to the characteristics of the product such as size and weight to ensure that the same group of pine nuts meets the predetermined standards, and each area has corresponding standard weight thresholds and size thresholds. For example, for large-sized pine nuts, the rule may stipulate that its standard size is a diameter of more than 10 mm and the weight is between 1.6 g and 1.8 g. High-resolution cameras are used to collect pine nut images without contact, obtain the actual number of pine nuts in each screening area, calculate the weight data, and quickly determine whether there is a deviation from the standard, thereby providing a basis for fault warning.

[0025] S200: Identify the characteristics of pine nuts based on the set of pine nut images, obtain the actual quantity set, and calculate to obtain the actual weight set.

[0026] Furthermore, step S200 of this application includes: According to the historical screening records of the same type of pine nut screening device, collect a set of sample pine nut images, and obtain the actual number of pine nuts in different sample pine nut images as the sample pine nut quantity to obtain the sample quantity set; use the set of sample pine nut images and the sample quantity set as input and supervision respectively, and train and test the convolutional neural network until convergence to obtain a pine nut quantity recognition plug-in; use the pine nut quantity recognition plug-in to identify the characteristics of pine nuts in several pine nut images of the set of pine nut images respectively, and output the actual quantity set.

[0027] Furthermore, this application also includes the following steps: Weigh the total weight of pine nuts in several screening areas to construct a set of total pine nut weights; perform mapping calculations based on the set of total pine nut weights and the actual quantity set, and output the actual weight set, where the actual weight is the average weight of a single pine nut.

[0028] Specifically, obtain all screening data records collected during the actual operation of the same type of pine nut screening equipment, including data such as images and quantities of pine nuts in each area. According to the past screening records of the same type of pine nut screening device, extract a large number of labeled sample images, and each image is accompanied by corresponding actual pine nut quantity data to obtain a set of sample pine nut images and a set of sample pine nut quantities. For example, assume that the set of sample images contains 1000 images, and based on this, the actual number of pine nuts in multiple images can be determined as follows: Image 1 has 18 pine nuts, Image 2 has 20 pine nuts, Image 3 has 21 pine nuts... to form a sample quantity set.

[0029] Using the sample pine nut images as input and the sample quantity as supervision, train the pine nut quantity recognition plug-in. Preprocess the set of sample pine nut images and the corresponding set of sample quantities obtained from the historical screening records, and uniformly adjust all images to a fixed size (e.g., 256×256 pixels) to ensure consistent input sizes. Normalize the pixel values, mapping [0, 255] to the range [0, 1]. To enhance the generalization ability of the model, perform data augmentation on the training set, such as random rotation (±15°), translation, scaling, and flipping. Divide the dataset into a training set and a validation set at a ratio of 80 / 20 for real-time effect monitoring during the training process. Select a regression model architecture based on convolutional layer - pooling layer - fully connected layer, including an input layer, convolutional layer, pooling layer, fully connected layer, and output layer. For a batch, input the preprocessed images into the model architecture for forward propagation to obtain the corresponding predicted quantity, calculate the loss using the mean squared error loss function, perform backpropagation using the Adam optimizer, and transfer the gradients and update the network weights of each layer. After each epoch, iterate through all training batches and use the average loss on the entire training set as the training error metric. After each epoch ends, evaluate the model performance using the validation set and calculate the MSE loss value of the validation set. Observe whether the validation set loss decreases. If the decrease amplitude is lower than a preset threshold (e.g., the change is less than 0.005), it may be approaching convergence. For example, the training loss in the initial epoch (epoch1) is 0.18, and the validation loss is 0.17; after 50 epochs, the training loss drops to 0.06, and the validation loss is 0.065; at the 150th epoch: the training loss is 0.032, and the validation loss remains at 0.034; starting from the 160th epoch, the validation loss fluctuates between 0.033 and 0.035 without an obvious decrease, meeting the early stopping condition.

[0030] When the validation set loss remains stable at a low value (e.g., 0.033 - 0.035) for multiple consecutive epochs and shows no significant decrease, it is considered that the model parameters have converged sufficiently. At this time, the model has learned the mapping relationship between the input images and the actual pine nut quantities. Save the trained model as a standard interface and deploy it to the production environment.

[0031] Embed the trained pine nut quantity recognition plug-in into the data processing module of the pine nut screening device. Input several pine nut images from the set of pine nut images into the pine nut quantity recognition plug-in for feature recognition. Analyze the pine nut features in the images through the plug-in and output the pine nut quantity of each detected area to form an actual quantity set, realizing automatic target counting.

[0032] Within each screening area, the sum of the weights of all pine nuts measured by a weighing device (such as a pressure sensor) is obtained to get the total weight of pine nuts in each area, thus obtaining a set of total pine nut weights. The set of total pine nut weights is a set of total weight data constructed by area after weighing pine nuts in multiple screening areas. For example, the weighing result in area 1 is 500 grams, in area 2 is 520 grams, and so on.

[0033] For each area, the actual number of pine nuts in that area has been obtained through image recognition, forming a set of actual numbers. Through mapping calculation, for each area, the total weight of that area is divided by the actual number to obtain the average weight of a single pine nut. For example, assume that the set of actual numbers (unit: grams) in several screening areas is {25, 26, 24, 25, 25}, and the corresponding set of total pine nut weights (unit: pieces) is {500, 520, 480, 510, 495}, then the set of actual weights (unit: grams / piece) is {20, 20, 20, 20.4, 19.8}. By weighing to obtain the total weight of pine nuts and combining with mapping calculation of the actual number, the average weight of a single pine nut in each screening area is accurately measured. When the data in a certain area is significantly abnormal, it can be regarded as an indication signal of equipment failure or error, which helps with timely maintenance.

[0034] S300: Based on the standard weight threshold, perform consistency analysis on the set of actual weights to obtain several screening consistency coefficients for several screening areas.

[0035] Furthermore, step S300 of the present application includes: Randomly select the first standard weight threshold of the first screening area and obtain the first actual weight; take the median of the first standard weight threshold as the first standard weight mean, calculate the deviation ratio between the first standard weight mean and the first actual weight, and set the reciprocal of the deviation ratio as the first screening consistency coefficient, and add it to the several screening consistency coefficients.

[0036] Specifically, for each screening area, the standard weight threshold presets a required range for the weight of pine nuts. For example, it is stipulated that the weight of pine nuts in a certain area should be between 19 grams and 21 grams. Randomly select the first standard weight threshold corresponding to the first screening area within the standard weight threshold, which defines the important requirements that the pine nuts in the first screening area should meet. At the same time, obtain the corresponding first actual weight in the set of actual weights.

[0037] For the first screening area, the median of the first standard weight threshold is taken as the first standard weight mean. For example, the median between 19 grams and 21 grams is 20 grams. Calculate the deviation ratio between the first standard weight mean and the first actual weight. By taking the absolute values of the first standard weight mean and the first actual weight, calculate the ratio of the absolute value to the first standard weight mean to obtain the relative deviation ratio. Based on the calculated deviation ratio, take its reciprocal as the first screening consistency coefficient and add it to several screening consistency coefficients. The screening consistency coefficient is used to reflect the consistency between the actual weight and the standard weight.

[0038] For other screening areas, the above consistency analysis is also carried out to obtain several screening consistency coefficients for several screening areas. Consistency analysis is a quantitative comparison and analysis method that compares the actual average weight of each screening area with the corresponding standard weight threshold, calculates its deviation, and measures the matching degree between the actual situation of each screening area and the preset standard. It is usually defined as the reciprocal of the deviation ratio, that is, the smaller the deviation, the larger the consistency coefficient, the more consistent, and vice versa, the smaller the consistency coefficient.

[0039] Through the calculation of the deviation ratio and the consistency coefficient, objectively quantify the deviation between the actual weight of pine nuts in each screening area and the preset standard. The higher the value of the consistency coefficient, the more consistent the actual weight and the standard within the area, and the higher the screening accuracy of the equipment; if the value is relatively low, it may indicate the existence of abnormal or failure risks.

[0040] S400: Continuously monitor and obtain several sequences of screening consistency coefficients within a preset time range, and perform mean calculation, fluctuation analysis, and trend fitting to obtain several mean consistency coefficients, several fluctuation coefficients, and several trend coefficients.

[0041] Furthermore, S400 of this application includes: Within a preset time range, continuously perform image acquisition and consistency analysis to obtain several sequences of screening consistency coefficients; respectively perform mean calculation on the several sequences of screening consistency coefficients to obtain several mean consistency coefficients; perform fluctuation analysis and trend fitting based on the several sequences of screening consistency coefficients respectively, and output several fluctuation coefficients and several trend coefficients.

[0042] Specifically, the preset time range is a continuous period of time set in advance during the pine nut screening process, such as a continuous 1 hour, 8 hours, or the monitoring period within a day. Through industrial cameras installed in each screening area, pine nut image data of several areas are continuously or regularly collected within the preset time range. At the same time, for each collected image, a consistency analysis method is adopted, that is, the actual number of pine nuts is determined through image acquisition, the total weight of pine nuts is obtained by weighing, and mapping calculation is performed based on the total weight and the actual number of pine nuts to determine the actual weight, which is compared with the standard weight threshold of this area to obtain the corresponding screening consistency coefficient. After each collection, a screening consistency coefficient is obtained, forming time series data, and several screening consistency coefficient sequences are obtained, including the screening consistency coefficient sequences corresponding to several screening areas.

[0043] The mean values of several screening consistency coefficient sequences are calculated respectively to obtain several consistency coefficient means, that is, the arithmetic mean of all consistency coefficients in each area is calculated to obtain the stable level of the overall screening consistency of each area. According to the several consistency coefficient means, the standard deviation of each screening consistency coefficient sequence in each area is calculated, and according to the ratio of the standard deviation to the mean value, several fluctuation coefficients of several screening areas are obtained.

[0044] A two-dimensional coordinate system is constructed based on each monitoring time node and its corresponding screening consistency coefficient, and curve fitting is performed to obtain several trend curves of several screening areas and the corresponding coefficients, which are used to reflect whether the trend is rising or falling. The trend coefficient is a quantitative index used to describe the change trend of data over time.

[0045] Through fluctuation analysis and trend analysis, the operating state of the pine nut screening equipment within the preset time range is comprehensively evaluated, revealing the consistency and long-term change trend of the equipment operation respectively. If the fluctuation coefficient is too high or the trend coefficient shows a large downward trend, it means that the equipment needs maintenance or adjustment. By responding to these warning signals in a timely manner, equipment failures can be reduced and production efficiency can be improved.

[0046] Furthermore, the present application further includes the following steps: The standard deviations of the several screening consistency coefficient sequences are calculated respectively to obtain several consistency coefficient standard deviations; according to the several consistency coefficient standard deviations and several consistency coefficient means, several fluctuation coefficients are calculated, where the fluctuation coefficient is the ratio of the consistency coefficient standard deviation to the consistency coefficient mean.

[0047] Specifically, the standard deviation of the consistency coefficient is the degree of dispersion between each data value and the sequence mean in the consistency coefficient sequence obtained in a certain area. The smaller the standard deviation, the smaller the data fluctuation and the more stable the result; the larger the standard deviation, the greater the fluctuation. For each screening area, take the consistency coefficient sequence obtained within the preset time range and calculate the standard deviation of this sequence using statistical methods. Calculate the square of the difference between each data and the mean, find its average value, and take the square root to obtain the standard deviation.

[0048] After obtaining the standard deviation and mean of the consistency coefficient sequence, calculate the fluctuation coefficient for each screening area. The fluctuation coefficient is obtained by the ratio of the standard deviation of the consistency coefficient to the mean of the consistency coefficient, and several fluctuation coefficients are obtained. Each screening area will obtain a fluctuation coefficient, and this value reflects the relative amplitude of the screening consistency coefficient fluctuating with time within this area. The several fluctuation coefficients include the fluctuation coefficients corresponding to several screening areas.

[0049] Exemplarily, assume that a certain screening area has collected 10 consistency coefficients within the preset time, and the specific values are [50, 52, 49, 51, 50, 50, 53, 48, 50, 51]. The calculated mean is 50.4, and the standard deviation (calculate the square of the difference between each value and the mean, find the average, and then take the square root) is 1.84, then the fluctuation coefficient is 0.0365. Through the ratio of the standard deviation to the mean (i.e., the fluctuation coefficient), determine the stability of the consistency index for each screening area. Similarly, calculate the corresponding fluctuation coefficients for other screening areas respectively, and form a set of several fluctuation coefficients.

[0050] By calculating the standard deviation of the continuously collected consistency coefficient sequence, obtain the standard deviation of the consistency coefficient for each screening area, and then calculate the fluctuation coefficient in combination with the mean of the consistency coefficient to quantify the fluctuation degree of each screening area and determine whether the device is operating unstably. If the fluctuation coefficient is high, it means that the operating state of the device is not stable enough and needs to be adjusted or maintained.

[0051] Furthermore, the present application further includes the following steps: Take the monitoring time node as the X-axis and the screening consistency coefficient as the Y-axis to construct a two-dimensional coordinate system; within the two-dimensional coordinate system, distribute and curve fit the several screening consistency coefficient sequences to obtain several trend curves; identify the several trend curves to obtain several trend coefficients, where the trend coefficient is the overall rising or falling ratio.

[0052] Specifically, set the preset monitoring time node (i.e., the time when the image is collected) as the X-axis, and set the screening consistency coefficient calculated at each time node as the Y-axis to construct a two-dimensional plane data graph for showing the changing trend of the data over time. Using statistical methods, perform trend analysis on the discrete data points in the two-dimensional coordinate graph, and obtain one or more curves through fitting methods (such as linear regression or polynomial fitting), and this curve describes the overall trend of the data points changing over time. For the consistency coefficient sequence in the constructed two-dimensional coordinate system, adopt curve fitting methods, such as using quadratic, polynomial and other curve fitting methods, and select the fitting function to minimize the error.

[0053] Map each group of time and the corresponding consistency coefficient into points on the two-dimensional plane. The data of all screening areas can independently form their own coordinate systems, or can be plotted in the same graph for comparison. Find out the trend relationship between these discrete points, and use the fitting algorithm to obtain the trend curve. Each group of consistency coefficient sequences will generate a trend curve, and several trend curves will be obtained for multiple screening areas to reflect the data trend.

[0054] Extract the slope (or other parameters reflecting the overall change ratio) from the obtained trend curve, and define it as the trend coefficient: if the slope k>0, the trend coefficient is positive, indicating an overall upward trend; if the slope k<0, the trend coefficient is negative, indicating an overall downward trend; the absolute value of the trend coefficient reflects the change rate. Each group of consistency coefficient sequences will generate a trend curve, and several trend curves will be obtained for multiple screening areas to reflect whether there are abnormalities in the data of each area.

[0055] Exemplarily, assume that the screening consistency coefficients collected at 10 consecutive time nodes in a certain screening area are as follows: [50, 50.5, 51, 50.8, 51.2, 51.5, 51.3, 51.7, 52, 52.2], and the corresponding time nodes (unit: minute) are T = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10]. Apply the least squares method to fit the straight line y = 0.22x + 50, where x is the time and y is the screening consistency coefficient.

[0056] Within the preset time range, take the screening consistency coefficient of each collected time node as the Y-axis data, and construct a two-dimensional coordinate system with the monitoring time node as the X-axis data. Through distribution analysis and curve fitting (such as linear regression) of these data points, obtain the trend curve, and extract the trend coefficient from it to reveal the changing direction of the consistency coefficient of each screening area over time, and help analyze whether the equipment operation is stable or whether there are problems of gradual deterioration. The trend coefficient (such as the slope of the fitted straight line) reflects the proportion of the overall increase or decrease of the screening consistency coefficient, and is an important indicator for judging the change of the equipment operation state and warning of the fault risk.

[0057] S500: If the mean value of any consistency coefficient, fluctuation coefficient, or trend coefficient does not meet the preset coefficient threshold, a fault warning is issued for the pine nut screening device.

[0058] Furthermore, S500 of this application includes: The preset coefficient threshold includes a consistency coefficient threshold, a fluctuation coefficient threshold, and a trend decline ratio threshold, where the preset coefficient threshold is set based on the pine nut specifications.

[0059] Furthermore, this application also includes the following steps: If the mean value of the consistency coefficient in any screening area is less than the consistency coefficient threshold and / or the fluctuation coefficient is greater than the fluctuation coefficient threshold and / or the decline ratio of the trend coefficient is greater than the trend decline ratio threshold, a fault warning is issued for the pine nut screening device.

[0060] Specifically, for each screening area, calculate the mean value of the consistency coefficient, the consistency fluctuation coefficient, and the consistency trend coefficient, and compare them with their respective preset thresholds. As long as any one of the triggering conditions is met, that is, any one of the mean value of the consistency coefficient, the fluctuation coefficient, and the trend coefficient does not meet the preset coefficient threshold, a fault warning signal is issued.

[0061] According to the pine nut specifications, determine the preset coefficient threshold to judge whether the equipment is operating normally. The preset coefficient threshold includes a consistency coefficient threshold, a fluctuation coefficient threshold, and a trend decline ratio threshold, which are respectively used to judge whether the mean value of the consistency coefficient, the fluctuation coefficient, or the trend coefficient is within the acceptable range.

[0062] If the mean value of the consistency coefficient in any screening area is lower than the consistency coefficient threshold, or the fluctuation coefficient in any screening area exceeds the fluctuation coefficient threshold, or the decline ratio of the trend coefficient in any screening area exceeds the trend decline ratio threshold, as long as any one of the conditions is met, immediately trigger a fault warning and notify the maintenance personnel to check the equipment. The preset coefficient threshold provides a benchmark for judging whether the equipment is operating normally, helps to detect potential problems in a timely manner, thereby improving production efficiency and product quality.

[0063] Conduct a detailed inspection of the screening area where the warning is triggered to identify possible fault causes. According to the inspection results, carry out necessary maintenance and adjustment to restore the normal operation of the screening device. Record the warning information and processing results for subsequent analysis and improvement. By responding to the fault warning in a timely manner, the maintenance personnel can take appropriate measures to avoid greater losses caused by equipment failures.

[0064] In summary, the fault prediction method for a fully automatic pine nut transfer and processing equipment provided by this application has the following technical effects: Collect pine nut images in several screening areas through a camera to obtain a pine nut image set. Among them, the pine nut specifications in each screening area are different, and the pine nut specifications include a standard weight threshold. Identify the characteristics of pine nuts based on the pine nut image set to obtain an actual quantity set, and calculate an actual weight set. Based on the standard weight threshold, perform consistency analysis on the actual weight set to obtain several screening consistency coefficients for several screening areas. Continuously monitor and obtain several screening consistency coefficient sequences within a preset time range, and perform mean calculation, fluctuation analysis, and trend fitting to obtain several consistency coefficient means, several fluctuation coefficients, and several trend coefficients. If any of the consistency coefficient means, fluctuation coefficients, or trend coefficients do not meet the preset coefficient threshold, a fault warning will be issued for the pine nut screening device. That is to say, by analyzing the fluctuation of the pine nut weight during the pine nut screening process, comprehensively analyze the operating state of the equipment, monitor the consistency coefficients of multiple screening areas, and detect slight but continuous deviations in advance during the screening process of different regions and different specifications, capture complex hidden faults such as equipment degradation, aging, and calibration imbalance, and issue early warnings to accurately judge the abnormalities in the initial stage of equipment operation, improving the accuracy and efficiency of fault prediction for the fully automatic transfer and processing equipment of pine nuts.

[0065] Embodiment 2. Based on the same inventive concept as the fault prediction method for a fully automatic transfer and processing equipment of pine nuts in the foregoing Embodiment 1, the present application also provides a fault prediction system for a fully automatic transfer and processing equipment of pine nuts. Please refer to the attached Figure 2 , the fault prediction system for a fully automatic transfer and processing equipment of pine nuts includes: An image acquisition module 11, which is used to collect pine nut images in several screening areas through a camera to obtain a pine nut image set. Among them, the pine nut specifications in each screening area are different, and the pine nut specifications include a standard weight threshold. A weight calculation module 12, which is used to identify the characteristics of pine nuts based on the pine nut image set to obtain an actual quantity set, and calculate an actual weight set. A consistency analysis module 13, which is used to perform consistency analysis on the actual weight set based on the standard weight threshold to obtain several screening consistency coefficients for several screening areas. A dynamic monitoring and analysis module 14, which is used to continuously monitor and obtain several screening consistency coefficient sequences within a preset time range, and perform mean calculation, fluctuation analysis, and trend fitting to obtain several consistency coefficient means, several fluctuation coefficients, and several trend coefficients. A threshold judgment module 15, which is used to issue a fault warning for the pine nut screening device if any of the consistency coefficient means, fluctuation coefficients, or trend coefficients do not meet the preset coefficient threshold.

[0066] Furthermore, the weight calculation module 12 in the fault prediction system for a fully automatic transfer and processing equipment of pine nuts is further used for: According to the historical screening records of the same type of pine nut screening device, collect a sample pine nut image set, and obtain the actual number of pine nuts in different sample pine nut images as the sample pine nut quantity to obtain a sample quantity set; use the sample pine nut image set and the sample quantity set to train and test a convolutional neural network with the sample pine nut images as the input and the sample quantity as the supervision until convergence to obtain a pine nut quantity recognition plug-in; use the pine nut quantity recognition plug-in to respectively perform pine nut feature recognition on several pine nut images in the pine nut image set and output an actual quantity set.

[0067] Further, the weight calculation module 12 in the fault prediction system of the automatic pine nut transfer and processing equipment is further configured to: Weigh the total weight of pine nuts in several screening areas to construct a total pine nut weight set; perform mapping calculation according to the total pine nut weight set and the actual quantity set and output an actual weight set, where the actual weight is the average weight of a single pine nut.

[0068] Further, the consistency analysis module 13 in the fault prediction system of the automatic pine nut transfer and processing equipment is further configured to: Randomly select a first standard weight threshold for the first screening area and obtain a first actual weight; use the median of the first standard weight threshold as the first standard weight average value, calculate the deviation ratio between the first standard weight average value and the first actual weight, and set the reciprocal of the deviation ratio as the first screening consistency coefficient and add it to several screening consistency coefficients.

[0069] Further, the dynamic monitoring and analysis module 14 in the fault prediction system of the automatic pine nut transfer and processing equipment is further configured to: Within a preset time range, continuously perform image acquisition and consistency analysis to obtain several screening consistency coefficient sequences; respectively calculate the average values of the several screening consistency coefficient sequences to obtain several consistency coefficient average values; perform fluctuation analysis and trend fitting according to the several screening consistency coefficient sequences respectively and output several fluctuation coefficients and several trend coefficients.

[0070] Further, the dynamic monitoring and analysis module 14 in the fault prediction system of the automatic pine nut transfer and processing equipment is further configured to: Respectively calculate the standard deviations of the several screening consistency coefficient sequences to obtain several consistency coefficient standard deviations; calculate several fluctuation coefficients according to the several consistency coefficient standard deviations and the several consistency coefficient average values, where the fluctuation coefficient is the ratio of the consistency coefficient standard deviation to the consistency coefficient average value.

[0071] Further, the dynamic monitoring and analysis module 14 in the fault prediction system of the automatic pine nut transfer and processing equipment is further configured to: Taking the monitoring time node as the X-axis and the screening consistency coefficient as the Y-axis, a two-dimensional coordinate system is constructed; within the two-dimensional coordinate system, the distribution and curve fitting of the several screening consistency coefficient sequences are performed to obtain several trend curves; the several trend curves are identified to obtain several trend coefficients, where the trend coefficient is the overall rising or falling ratio.

[0072] Further, the threshold judgment module 15 in the fault prediction system of the full-automatic pine nut transfer and processing equipment is further configured to: The preset coefficient thresholds include a consistency coefficient threshold, a fluctuation coefficient threshold, and a trend decline ratio threshold, where the preset coefficient thresholds are set based on the pine nut specifications.

[0073] Further, the threshold judgment module 15 in the fault prediction system of the full-automatic pine nut transfer and processing equipment is further configured to: If the average value of the consistency coefficient in any screening area is less than the consistency coefficient threshold and / or the fluctuation coefficient is greater than the fluctuation coefficient threshold and / or the decline ratio of the trend coefficient is greater than the trend decline ratio threshold, a fault warning is given to the pine nut screening device.

[0074] The various embodiments in this specification are described in a progressive manner, and the key points of each embodiment are the differences from other embodiments. The foregoing Figure 1 The fault prediction method and specific examples of the full-automatic pine nut transfer and processing equipment in the first embodiment are equally applicable to the fault prediction system of the full-automatic pine nut transfer and processing equipment in this embodiment. Through the foregoing detailed description of the fault prediction method of the full-automatic pine nut transfer and processing equipment, those skilled in the art can clearly know the fault prediction system of the full-automatic pine nut transfer and processing equipment in this embodiment. Therefore, for the sake of brevity of the specification, it will not be elaborated here. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the description of the method part.

[0075] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0076] Obviously, those skilled in the art can make various changes and modifications to this application without departing from the spirit and scope of this application. Thus, if these modifications and variations of this application fall within the scope of this application and its equivalent technologies, this application also intends to include these changes and modifications.

Claims

1. A fault prediction method for a fully automatic transfer and processing equipment of pine nuts, characterized in that, Including: Collect pine nut images within several screening areas through a camera to obtain a pine nut image set. Among them, the pine nut specifications in each screening area are different, and the pine nut specifications include a standard weight threshold; Perform pine nut feature recognition based on the pine nut image set to obtain an actual quantity set, and calculate to obtain an actual weight set; Based on the standard weight threshold, conduct consistency analysis on the actual weight set to obtain several screening consistency coefficients for several screening areas; Continuously monitor to obtain several screening consistency coefficient sequences within a preset time range, and perform mean calculation, fluctuation analysis, and trend fitting to obtain several consistency coefficient means, several fluctuation coefficients, and several trend coefficients; If any one of the consistency coefficient means, fluctuation coefficients, or trend coefficients does not meet the preset coefficient threshold, a fault warning is given to the pine nut screening device.

2. The fault prediction method of a fully automatic flowing and processing equipment for pine nuts according to claim 1, wherein, Performing pine nut feature recognition based on the pine nut image set to obtain an actual quantity set, including: According to the historical screening records of the same type of pine nut screening device, collect a sample pine nut image set, and obtain the actual number of pine nuts in different sample pine nut images as the sample pine nut quantity to obtain a sample quantity set; Using the sample pine nut images as input and the sample quantity as supervision, train and test the convolutional neural network with the sample pine nut image set and the sample quantity set until convergence to obtain a pine nut quantity recognition plug-in; Using the pine nut quantity recognition plug-in, perform pine nut feature recognition on several pine nut images in the pine nut image set respectively, and output an actual quantity set.

3. The fault prediction method of a fully automatic flowing and processing device for pine nuts according to claim 1, characterized in that, Calculating to obtain an actual weight set, including: Weigh the total weight of pine nuts in several screening areas to construct a total pine nut weight set; Perform mapping calculation based on the total pine nut weight set and the actual quantity set, and output an actual weight set, where the actual weight is the average weight of a single pine nut.

4. The fault prediction method of a fully automatic transfer and processing equipment for pine nuts according to claim 1, characterized in that, Based on the standard weight threshold, conducting consistency analysis on the actual weight set, including: Randomly select the first standard weight threshold of the first screening area and obtain the first actual weight; Take the median of the first standard weight threshold as the first standard weight mean, calculate the deviation ratio between the first standard weight mean and the first actual weight, and set the reciprocal of the deviation ratio as the first screening consistency coefficient, and add it to several screening consistency coefficients.

5. The fault prediction method for a fully automatic flowing and processing device of pine nuts according to claim 1, characterized in that, Continuously monitor to obtain several screening consistency coefficient sequences within a preset time range, and perform mean calculation, fluctuation analysis, and trend fitting, including: Within the preset time range, continuously perform image collection and consistency analysis to obtain several screening consistency coefficient sequences; Perform mean calculation on the several screening consistency coefficient sequences respectively to obtain several consistency coefficient means; Based on the several screening consistency coefficient sequences, perform fluctuation analysis and trend fitting respectively, and output several fluctuation coefficients and several trend coefficients.

6. A fault prediction method for a fully automatic transfer and processing device for pine nuts according to claim 5, characterized in that, Performing fluctuation analysis based on the several screening consistency coefficient sequences respectively, including: Perform standard deviation calculation on the several screening consistency coefficient sequences respectively to obtain several consistency coefficient standard deviations; Based on the several standard deviations of the consistency coefficients and the several mean values of the consistency coefficients, several fluctuation coefficients are calculated, where the fluctuation coefficient is the ratio of the standard deviation of the consistency coefficient to the mean value of the consistency coefficient.

7. A fault prediction method for a fully automatic transfer and processing equipment of pine nuts according to claim 5, characterized in that, Perform trend fitting respectively according to the several screened consistency coefficient sequences, including: Construct a two-dimensional coordinate system with the monitoring time node as the X-axis and the screened consistency coefficient as the Y-axis; Within the two-dimensional coordinate system, perform distribution and curve fitting on the several screened consistency coefficient sequences to obtain several trend curves; Identify the several trend curves to obtain several trend coefficients, where the trend coefficient is the overall rising or falling ratio.

8. A fault prediction method for a fully automatic transfer and processing equipment of pine nuts according to claim 1, characterized in that, The preset coefficient thresholds include a consistency coefficient threshold, a fluctuation coefficient threshold, and a trend decline ratio threshold, where the preset coefficient thresholds are set based on the pine nut specifications.

9. A fault prediction method for a fully automatic transfer and processing device of pine nuts according to claim 8, characterized in that, If the mean value of the consistency coefficient in any screened area is less than the consistency coefficient threshold and / or the fluctuation coefficient is greater than the fluctuation coefficient threshold and / or the decline ratio of the trend coefficient is greater than the trend decline ratio threshold, a fault warning is given to the pine nut screening device.

10. A fault prediction system for a fully automatic transfer and processing equipment of pine nuts, characterized in that, Steps for implementing the fault prediction method of the fully automatic transfer and processing equipment for pine nuts according to any one of claims 1 to 9, the fault prediction system of the fully automatic transfer and processing equipment for pine nuts includes: An image acquisition module, configured to collect pine nut images in several screened areas through a camera to obtain a pine nut image set, where the pine nut specifications in each screened area are different, and the pine nut specifications include a standard weight threshold; A weight calculation module, configured to perform pine nut feature recognition according to the pine nut image set to obtain an actual quantity set and calculate an actual weight set; A consistency analysis module, configured to perform consistency analysis on the actual weight set based on the standard weight threshold to obtain several screened consistency coefficients in several screened areas; A dynamic monitoring and analysis module, configured to continuously monitor and obtain several screened consistency coefficient sequences within a preset time range, and perform mean value calculation, fluctuation analysis, and trend fitting to obtain several mean values of the consistency coefficients, several fluctuation coefficients, and several trend coefficients; A threshold judgment module, configured to give a fault warning to the pine nut screening device if any mean value of the consistency coefficient, fluctuation coefficient, or trend coefficient does not meet the preset coefficient threshold.

Images