Material distribution method and system based on product length and storage medium

Abstract

The invention relates to the technical field of automatic control, and discloses a material distribution method and system based on product length and a storage medium. The material distribution system comprises a feeding module, a separation module, a plurality of separation rails, a first detection unit and a second detection unit. Starting a feeding module to convey products according to a specified speed, and starting a first detection unit and a second detection unit at the same time; whether the product arrives at the first detection unit or not is judged cyclically, whether the second detection unit continuously detects the product within the specified duration time or not and detects that the product does not exist when the specified duration time is up is judged, when the specified duration time is up, the material distribution action on the product is triggered and recorded, and otherwise, a standby material distribution program is triggered; false triggering or repeated counting of an original counting mode can be avoided as much as possible, the second detection unit detects that the product exceeds the specified duration time, the type change of the product can be judged, and a standby material distribution program is started to avoid wrong material distribution.

Description

Technical Field

[0001] The present application relates to the technical field of automatic control, and in particular to a material dividing method, system and storage medium based on product length. Background Art

[0002] In recent years, the speed of production lines has been getting faster and faster. Products often experience jamming and false triggering during lane and material separation, resulting in counting errors. This design method does not require professional technology, and various input and output signals can be quickly connected according to the drawings. This creates good conditions for the rapid implementation and completion of the project.

[0003] Under the current high-speed production line demand of manufacturing enterprises and the increasing traceability of code scanning, a simple material sorting method is created, which can not only solve the problem of scanning codes in batches at one time, but also solve the errors in material sorting, thereby saving hardware costs. There is no need to understand the internal structure. The signal lines can be inserted accordingly according to the design method of this scheme. Moreover, this design solves the erroneous material sorting caused by the lack of spacing between consecutive products in most companies under high-speed environments, and also solves the problem of scanning codes in batches. The method of covering the buffer area once is used to accurately count the scanned codes and associate them with the boxes after sorting. This innovation is compatible and only requires the addition of one cylinder and two electric eyes to achieve accurate material sorting. This innovation is not only to solve the problem of material sorting on the production line, but also to solve errors such as erroneous recursion after scanning and entering the production line, thereby reducing the error rate.

[0004] Although there are many designs on the market, they cannot be closely integrated with code scanning equipment or cannot be used in the field of digital collection on the production line. Most of them require additional code scanning triggers, which requires a lot of wiring work, which greatly increases the cost. They are not suitable for small and micro enterprises or individuals who are not familiar with electronics, and increase the labor cost on site. Therefore, this solution aims to solve the accuracy of material distribution and the timing of code scanning trigger. Summary of the invention

[0005] In order to provide a method, system and storage medium that can efficiently and accurately divide products based on length, the present application provides a method, system and storage medium for dividing products based on product length.

[0006] In a first aspect, the present application provides a method for dividing materials based on product length, which adopts the following technical solution:

[0007] A method for dividing materials based on product length, comprising:

[0008] S100, constructing a material dividing system; the material dividing system comprises a feeding module, a lane dividing module and at least two lane dividing tracks connected in sequence;

[0009] Among them, the lane module is configured with a first detection unit for detecting whether the product reaches the lane module, and one side of the feeding module is configured with a second detection unit for detecting the product;

[0010] S200, start the feeding module to convey the product at a specified speed, and at the same time start the first detection unit and the second detection unit;

[0011] S300, repeatedly determine whether the product has reached the first detection unit. If so, proceed to step S400;

[0012] S400, determine whether the second detection unit continuously detects the product within a specified duration and detects that the product does not exist when the specified duration arrives. If so, proceed to S500 when the specified duration arrives; otherwise, trigger the backup material distribution program;

[0013] S500, trigger the material distribution action for the product and record it.

[0014] By adopting the above technical solution, two detection units are used in the present invention. The first detection unit can be set at the buffer area for material distribution, that is, the lane module, to detect whether the product is in place. The second detection unit is set on the side of the feeding module in the advancing direction. When the product continuously enters the buffer area and reaches the position of the second detection unit for a specified duration and the first detection unit also detects it, material distribution is performed. This can avoid mis-triggering or inaccurate triggering and repeated counting of the original counting method; in addition, when the second detection unit detects the product for more than the specified duration, it can be determined that the product type has changed, and the backup material distribution program is started to avoid incorrect material distribution.

[0015] Optionally, the triggering of the backup material distribution program includes:

[0016] S401, obtain the time point when the second detection unit detects the existence of the product and the time point when the signal indicating the non-existence of the product is first detected ;

[0017] S402, determine whether it satisfies , if it satisfies, proceed to step S500; otherwise, proceed to step S403;

[0018] S403, repeatedly determine whether the specified duration has arrived. If so, proceed to step S404;

[0019] S404, drive the second detection unit to move in the direction opposite to the movement direction of the product, and at the arrival time point Stop and reset when

[0020] S405, Calculate and obtain the product length of the product, and return to step S200.

[0021] By adopting the above technical solution, two situations are considered. One is the shorter type of product, and the other is the longer type of product. For the shorter type of product, meeting the condition, directly enter step S500 and adopt the method of mechanical hand clamping and sorting, which can save the overall sorting time and is suitable for the scenario with a large product feeding density; for the longer type of product, when the specified duration arrives, to obtain the actual length of the product and improve the subsequent material separation accuracy, and at the same time to improve the sorting efficiency, adopt the method of driving the second detection unit to move relative to the product feeding direction to quickly obtain the product length.

[0022] Optionally, the configuration method of the specified duration includes;

[0023]

[0024] Among them, is the specified ideal duration, is the correction factor positively correlated with the specified speed.

[0025] By adopting the above technical solution, since the processes of clamping, sorting, and lane delivery take time, configuring at the millisecond level can appropriately trigger step S500, further improve the sorting efficiency, and reduce the harm caused by problems such as sorting jams.

[0026] Optionally, the process of triggering the material separation action of the product and recording in S500 includes:

[0027] S51, Determine the lane track to which the product belongs in combination with the product length;

[0028] S52, Trigger barcode scanning and recording, and the data is dynamically bound to the lane track and packaging box number of the product;

[0029] S53, Start the lane module to send the product to the corresponding lane track.

[0030] By adopting the above technical solution, the existing machine vision technology can be used to optimize the product classification model, and prominent marks related to the product length are added to the training pictures and sampling pictures, which helps to improve the classification accuracy.

[0031] Optionally, the time interval between step S52 and step S53 is controlled within 50 - 200ms.

[0032] By adopting the above technical solution, the preparatory work before sending to the corresponding sub-track can be completed quickly, reducing errors such as incorrect recurrence after scanning and recording, and reducing the error rate.

[0033] Optionally, it further includes:

[0034] S600, determine whether the material distribution is overtime or jammed. If so, trigger an audible and visual alarm and pause the production line; otherwise, return to step S200.

[0035] In a second aspect, the present application provides a material distribution system based on the product length, adopting the following technical solution:

[0036] A material distribution system based on the product length, the material distribution system includes a feeding module, a sub-track module and at least two sub-tracks connected in sequence;

[0037] Wherein, the sub-track module is configured with a first detection unit for detecting whether the product reaches the sub-track module, and one side of the feeding module is configured with a second detection unit for detecting the product;

[0038] It further includes:

[0039] A control unit, used to start the feeding module to convey the product at a specified speed, and at the same time start the first detection unit and the second detection unit;

[0040] Circularly judge that when the product arrives at the first detection unit, judge whether the second detection unit continuously detects the product within a specified duration and the product is not detected when the specified duration arrives. If so, enter S500 when the specified duration arrives; otherwise, trigger a backup material distribution program;

[0041] S500, trigger the material distribution action on the product and record it.

[0042] Optionally, the control unit is a MicroPython embedded board or an IO card.

[0043] By adopting the above technical solution, using a MicroPython embedded board to control the material distribution, there is no need to purchase an additional PLC, and it can be used as an integrated material distribution module independent of the computer.

[0044] Optionally, the specified duration is dynamically configured through an external interface.

[0045] By adopting the above technical solution, the specified duration can be adjusted at any time according to the actual situation, improving the flexibility of the material distribution solution.

[0046] In a third aspect, the present application provides a storage medium, adopting the following technical solution:

[0047] A storage medium stores a program of the material sorting method based on the product length described in any one of the above.

[0048] In summary, the present application includes at least one of the following beneficial technical effects:

[0049] 1. In the present invention, two detection units are adopted. The first detection unit can be set at the buffer area for material sorting, that is, at the lane module, to detect whether the product is in place. The second detection unit is set on the side of the advancing direction of the feeding module. When the product continuously enters the buffer area and reaches the position of the second detection unit for a specified duration and the first detection unit also detects it, material sorting is performed. This can avoid mis-triggering or inaccurate triggering and repeated counting of the original counting method. In addition, when the second detection unit detects that the product exceeds the specified duration, it can be determined that the product type has changed, and the backup material sorting program is started to avoid incorrect material sorting.

[0050] 2. The present invention considers two situations. One is the shorter type of product, and the other is the longer type of product. For the shorter type of product, when the condition is met, directly entering step S500 and using the mechanical hand to clamp and sort can save the overall sorting time and is suitable for the scenario with a large feeding density of products. For the longer type of product, when the specified duration arrives, in order to obtain the actual length of the product and improve the subsequent material sorting accuracy, and at the same time to improve the sorting efficiency, the second detection unit is driven to move relative to the product feeding direction to quickly obtain the product length. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 is a schematic flow chart of the material sorting method based on the product length in the present invention;

[0052] Figure 2 is a partial structural schematic diagram of the material sorting system in the present invention.

[0053] Reference numerals: 1. Feeding module; 2. Lane module; 3. First detection unit; 4. Second detection unit. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0054] The following details the embodiments of the present application, and the examples of the embodiments are shown in the drawings.

[0055] In the description of this specification, the description with reference to the terms "certain embodiments", "one embodiment", "some embodiments", "schematic embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials, or characteristics described in connection with the embodiments or examples are included in at least one embodiment or example of this application. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiments or examples. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples.

[0056] An embodiment of this application discloses a material separation method based on the length of a product. Referring to Figure 1 and Figure 2 , a material separation method based on the length of a product includes:

[0057] S100, build a material separation system; the material separation system includes a feeding module 1, a lane splitting module 2, and at least two lane splitting tracks connected in sequence;

[0058] Among them, the lane splitting module 2 is configured with a first detection unit 3 for detecting whether the product reaches the lane splitting module 2, and one side of the feeding module 1 is configured with a second detection unit 4 for detecting the product;

[0059] S200, start the feeding module 1 to convey the product at a specified speed, and at the same time start the first detection unit 3 and the second detection unit 4;

[0060] S300, repeatedly determine whether the product reaches the first detection unit 3. If so, enter step S400;

[0061] S400, determine whether the second detection unit 4 continuously detects the product within a specified duration and the product is not detected when the specified duration arrives. If so, enter S500 when the specified duration arrives, otherwise trigger the standby material separation program;

[0062] S500, trigger the material separation action on the product and record it. The material separation action can be bound to the scanned code data. Specifically, a solenoid valve can be used to drive a cylinder to perform lane splitting.

[0063] By adopting the above technical solution, in the present invention, electric eyes can be used as the two detection units. The first detection unit 3 can be set at the material separation buffer area, that is, the lane splitting module 2, to detect whether the product is in place, and the second detection unit 4 is set on the side of the advancing direction of the feeding module 1. When the product continuously enters the buffer area and reaches the position of the second detection unit 4 for a specified duration When the first detection unit 3 also detects it, the material is separated, which can avoid the mis-triggering or inaccurate triggering and repeated counting of the original counting method. In addition, when the second detection unit 4 detects that the product exceeds the specified duration, it can be determined that the product type has changed, and the standby material separation program is started to avoid incorrect material separation. The solenoid valve can be used to control the driving of the diverging module 2 to diverge, drive the guide rail to move, and send the product to the corresponding diverging track entrance.

[0064] Optionally, the triggering of the standby material separation program includes:

[0065] S401, obtaining the time point when the second detection unit 4 detects the existence of the product and the time point when the non-existence signal of the product is first detected ;

[0066] S402, determining whether it satisfies , if it satisfies, enter step S500, otherwise enter step S403;

[0067] S403, repeatedly determining whether the specified duration arrives, if so, enter step S404;

[0068] S404, driving the second detection unit 4 to move in the direction opposite to the movement direction of the product, and stopping and resetting at the arrival time point ;

[0069] S405, calculating and obtaining the product length of the product, and returning to step S200.

[0070] By adopting the above technical solution, two situations are considered. One is the shorter type of product, and the other is the longer type of product. For the shorter type of product, when the condition of is satisfied, directly entering step S500 and using the method of clamping and sorting by the manipulator can save the overall sorting time and is suitable for the scenario with a large product feeding density; for the longer type of product, when the specified duration arrives, in order to obtain the actual length of the product to improve the subsequent material separation accuracy, and at the same time, in order to improve the sorting efficiency, the method of driving the second detection unit 4 to move relative to the product feeding direction is adopted to quickly obtain the product length.

[0071] Optionally, the configuration method of the specified duration includes;

[0072]

[0073] Among them, is the specified ideal duration, is the correction factor positively correlated with the specified speed.

[0074] By adopting the above technical solution, since the processes of clamping, sorting, and diverting and delivering take time, a millisecond-level can be used to appropriately trigger step S500 in advance, further improving the sorting efficiency and reducing the harm caused by problems such as sorting jams.

[0075] Optionally, the process of triggering the material distribution action for the product and recording in S500 includes:

[0076] S51, determining the diverting track to which the product belongs in combination with the product length;

[0077] S52, triggering code scanning and recording, and dynamically binding the data to the diverting track of the product and the packing box number;

[0078] S53, starting the diverting module 2 to send the product to the corresponding diverting track.

[0079] By adopting the above technical solution, the existing machine vision technology can be used to optimize the classification model of the product, and prominent marks related to the product length are added to the training pictures and sampling pictures, which helps to improve the classification accuracy.

[0080] In the present invention, the classification model can adopt a Convolutional Neural Network (CNN). It can automatically extract the features of data through local connection, weight sharing, and spatial downsampling, greatly reducing the number of parameters while improving the robustness of the model, automatically extracting features, reducing the workload of manually designing features, having a certain invariance to translation, rotation, and scaling, and parameter sharing greatly reducing the computational complexity.

[0081] The convolutional layer of the classification model is used to extract the local features of the input data. A convolutional kernel (Filter) is used for a small weight matrix (such as 3×3, 5×5), slides on the input data, calculates the weighted sum of the local area, and the stride reflects the step size of each movement of the convolutional kernel (such as 1 or 2). The larger the stride, the smaller the output size. Zero padding is added to the edge of the input data (such as same padding to keep the output size unchanged). Each convolutional kernel generates a feature map, and multiple convolutional kernels can extract different features.

[0082] The training process of a convolutional neural network revolves around data, model structure, and optimization strategies. The core lies in iteratively adjusting parameters to enable the network to gradually capture data features. At the beginning of training, a labeled dataset needs to be prepared and preprocessed, including normalizing pixel values to the range of 0 - 1 to accelerate convergence. Meanwhile, data augmentation operations such as randomly rotating, cropping, or flipping the images are performed. This not only expands the limited data volume but, more importantly, forces the network to learn rotational and translational invariance, enhancing the model's generalization ability. When constructing the network architecture, the convolutional layer automatically extracts spatial features through the characteristics of local receptive fields and weight sharing, and introduces non-linearity with the ReLU activation function. The pooling layer gradually reduces the resolution of the feature map to expand the receptive field, and the fully connected layer finally maps high-order features to classification results.

[0083] Parameter initialization usually adopts the Xavier or He method, adjusting the initial weight range according to the number of input and output neurons to avoid the premature vanishing or explosion of gradients in the shallow network. In the forward propagation stage, after the input data undergoes transformations through each layer to obtain the prediction result, the cross-entropy loss function is used to quantify the difference between the predicted value and the true label. At this time, the backpropagation algorithm starts to calculate the gradients of the loss with respect to the parameters layer by layer. Optimizers such as Stochastic Gradient Descent (SGD) or Adam use these gradients to update the weights. The design of the momentum term can smooth the parameter update trajectory, and the adaptive learning rate mechanism assigns different update amplitudes to different parameters.

[0084] The learning rate, as a key hyperparameter controlling the step size of parameter updates, often adopts strategies such as cosine annealing or staged decay for dynamic adjustment. A larger step size is used in the initial stage to quickly approach the optimal region, and fine-tuning is performed in the later stage to avoid oscillations. To prevent the network from overly relying on local neurons, the Dropout technique randomly masks some neurons during forward propagation, forcing the remaining units to cooperate in learning robust features. The batch normalization layer alleviates the problem of gradient vanishing by normalizing the distribution of intermediate layer activation values and has a slight regularization effect at the same time.

[0085] During the training process, it is necessary to continuously monitor the performance of the training set and the validation set. When the validation loss has not improved for multiple consecutive rounds, the early stopping mechanism is triggered to prevent overfitting. The trained model needs to be evaluated for generalization performance on an independent test set, and the recognition effects of each category are analyzed through a confusion matrix. In the model tuning stage, hyperparameters such as the convolutional kernel size, network depth, and regularization strength may be adjusted. The entire process exhibits the characteristics of spiral optimization and requires repeated verification of the combined effects of different configurations. Before final deployment, visual analysis of error samples is also performed to observe the activation patterns of the convolutional layer to diagnose the rationality of feature extraction, forming a complete closed-loop from data understanding to model improvement.

[0086] The input data of the classification model passes through operations such as convolution, activation, and pooling layer by layer, and finally outputs the prediction result.

[0087] Optionally, the time interval between step S52 and step S53 is controlled within 50 - 200 ms.

[0088] By adopting the above technical solution, the preparatory work before sending the product to the corresponding lane track can be completed quickly, reducing errors such as incorrect recurrence after the code scanning record, and reducing the error rate.

[0089] Optionally, it further includes:

[0090] S600, determining whether the material distribution is timed out or jammed. If so, triggering an audible and visual alarm and pausing the production line; otherwise, returning to step S200.

[0091] The embodiment of the present application also discloses a material distribution system based on the product length. The material distribution system includes a feeding module 1, a lane dividing module 2, and at least two lane tracks connected in sequence;

[0092] Among them, the lane dividing module 2 is configured with a first detection unit 3 for detecting whether the product reaches the lane dividing module 2, and one side of the feeding module 1 is configured with a second detection unit 4 for detecting the product;

[0093] It further includes:

[0094] A control unit, configured to start the feeding module 1 to convey the product at a specified speed, and at the same time start the first detection unit 3 and the second detection unit 4;

[0095] Circularly judge that when the product arrives at the first detection unit 3, judge whether the second detection unit 4 continuously detects the product within a specified duration and the product is not detected when the specified duration arrives. If so, enter S500 when the specified duration arrives; otherwise, trigger a backup material distribution program;

[0096] S500, triggering the material distribution action for the product and recording it.

[0097] Optionally, the control unit is a MicroPython embedded board or an IO card.

[0098] By adopting the above technical solution, using a MicroPython embedded board to control the material distribution does not require additional procurement of a PLC and can be used as an integrated material distribution module independent of the computer.

[0099] Optionally, the specified duration is dynamically configured through an external interface.

[0100] By adopting the above technical solution, the specified duration can be adjusted at any time according to the actual situation, improving the flexibility of the material distribution solution.

[0101] An embodiment of the present application also discloses a storage medium storing a program of the material separation method, system and storage medium based on product length described in any one of the above.

[0102] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present application. Those of ordinary skill in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present application.

Claims

1. A material separation method based on the product length, characterized in that, Including: S100, building a material separation system; the material separation system includes a feeding module (1), a lane splitting module (2) and at least two lane splitting tracks connected in sequence. Wherein, the lane splitting module (2) is configured with a first detection unit (3) for detecting whether the product reaches the lane splitting module (2), and one side of the feeding module (1) is configured with a second detection unit (4) for detecting the product. S200, starting the feeding module (1) to convey the product at a specified speed, and at the same time starting the first detection unit (3) and the second detection unit (4). S300, repeatedly judging whether the product reaches the first detection unit (3), if so, entering step S400. S400, determine whether the second detection unit (4) continuously detects the product within a specified duration and detects that the product does not exist when the specified duration arrives. If so, enter S500 when the specified duration arrives; otherwise, trigger the standby material distribution program S500, triggering a material separation action on the product and recording it.

2. The material separation method based on the product length according to claim 1, characterized in that The triggering of the backup material separation program includes: S401, obtain the time points when the second detection unit (4) detects the presence of the product and the time points when the non-existence signal of the product is detected for the first time ; S402, Determine whether the condition is met. If it is met, proceed to step S500; otherwise, proceed to step S403; , if satisfied, go to step S500, otherwise go to step S403; S403, repeatedly determine whether the specified duration has been reached. If so, proceed to step S404; S404, drive the second detection unit (4) to move in the direction opposite to the product, and stop and reset at the arrival time point when it arrives; S405, calculating and obtaining the product length of the product, and returning to step S200.

3. The material separation method based on the product length according to claim 2, characterized in that, The specified duration The configuration method includes; wherein, is a specified ideal duration, is a correction factor positively correlated with the specified speed.

4. The material separation method based on the product length according to claim 2, characterized in that In the said S500, the process of triggering a material separation action on the product and recording it includes: S51, determining the lane splitting track to which the product belongs in combination with the product length. S52, triggering a barcode scanning record, and dynamically binding the data to the lane splitting track of the product and the packing case number. S53, starting the lane splitting module (2) to send the product to the corresponding lane splitting track.

5. The material separation method based on the product length according to claim 4, wherein The time interval between step S52 and step S53 is controlled within 50 - 200 ms.

6. The material separation method based on the product length according to claim 4, characterized in that Also including: S600, judging whether the material separation is timed out or jammed, if so, triggering an audible and visual alarm and pausing the production line, otherwise returning to step S200.

7. A material sorting system based on the length of the product, characterized in that, The material separation system includes a feeding module (1), a lane splitting module (2) and at least two lane splitting tracks connected in sequence. Wherein, the lane splitting module (2) is configured with a first detection unit (3) for detecting whether the product reaches the lane splitting module (2), and one side of the feeding module (1) is configured with a second detection unit (4) for detecting the product. Also including: A control unit for starting the feeding module (1) to convey the product at a specified speed, and at the same time starting the first detection unit (3) and the second detection unit (4). When it is cyclically determined that the product arrives at the first detection unit (3), it is determined whether the second detection unit (4) continuously detects the product within the specified duration and detects that the product does not exist when the specified duration arrives. If so, enter S500 when the specified duration arrives; otherwise, trigger the standby material distribution program S500, triggering a material separation action on the product and recording it.

8. The material separation method based on the product length according to claim 7, wherein The control unit is a MicroPython embedded board or an IO card.

9. The material separation method based on the product length according to claim 7, wherein The specified duration Is dynamically configured through an external interface.

10. A storage medium, characterized in that, Storing a program of the material separation method based on product length as described in any one of claims 1 - 6.

Images