Binding force adjusting method and system of banding machine

Abstract

The invention relates to the technical field of automatic control, in particular to a binding force adjusting method and system of a binding machine. The method comprises the following steps: acquiring parameter items corresponding to each sample in a binding force test set, wherein the parameter items comprise volume, weight and friction force; calculating the volume weight, the weight weight and the friction force weight of the sample; on the basis of the weighted mean value and the weighted value of each parameter item of the sample, a fluctuation index of the parameter item is obtained; penalty parameters of the parameter items are calculated, wherein the penalty parameters are in negative correlation with fluctuation indexes of the parameter items; and training the support vector regression model based on the binding force of the sample, the weight of each parameter item and the penalty parameter to realize the binding force adjustment of the banding machine, so that the accuracy of the binding force adjustment of the banding machine can be effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of automatic control, and particularly to a method and system for adjusting the tightening force of a strapping machine. Background Art

[0002] Strapping machines can be applied in industries such as packaging, logistics, and warehousing, and are mainly used for strapping packaged items, stabilizing goods or materials, etc.

[0003] The tightening force is one of the key parameters in the strapping process. By setting the tightening force, the strapping of the item to be strapped can be achieved. The magnitude of the tightening force directly affects the stability, appearance, and safety during transportation of the packaged item. Excessive tightening force may cause deformation or damage to the packaged item, while too small a tightening force may result in insecure strapping of the packaged item, increasing the risk of damage to the goods during transportation. Therefore, when strapping different types of items, a method for precisely controlling the tightening force is needed to meet the strapping requirements of different items.

[0004] During the strapping process, the volume, friction, weight, etc. of the item to be strapped will all affect the strapping effect, and the requirements for the tightening force will change according to the different characteristics of the item. For example, for lightweight items, a relatively small strapping force can be set, while for heavy or irregular items, a stronger strapping force is required.

[0005] Based on this, how to intelligently adjust the tightening force of the strapping machine according to the relevant parameters of the item to be strapped after obtaining the relevant parameters of the item to be strapped, so that the strapping machine can achieve the purpose of strapping the item while avoiding excessive squeezing or damage to the item by the strap, is a problem that those skilled in the art need to solve currently. Summary of the Invention

[0006] In order to solve the technical problem of how to intelligently adjust the tightening force of the strapping machine according to the relevant parameters of the item to be strapped after obtaining the relevant parameters of the item to be strapped, so that the strapping machine can achieve the purpose of strapping the item while avoiding excessive squeezing or damage to the item by the strap, the present invention provides a method and system for adjusting the tightening force of a strapping machine.

[0007] In a first aspect, the present invention provides a method for adjusting the tightening force of a strapping machine, adopting the following technical solution: A method for adjusting the tightening force of a strapping machine includes the steps: Obtain the parameter items corresponding to each sample in the binding force test set. The parameter items include volume, weight, and friction force. Obtain the volume index of the sample based on the difference between the sample volume and the volumes of other samples, and obtain the weight index and friction force index of the sample. Obtain the volume weight of the sample based on the sum of the sample volume index, weight index, and friction force index, and obtain the weight weight and friction force weight of the sample. Obtain the weighted mean of each parameter item of the sample, and calculate the fluctuation index of this type of parameter item based on the weighted values and weighted mean of the parameter items of each sample. Calculate the penalty parameter of the parameter item. The penalty parameter is negatively correlated with the fluctuation index of this type of parameter item. Train a support vector regression model based on the binding force of the sample, the weights of each parameter item, and the penalty parameter to achieve the adjustment of the binding force of the strapping machine.

[0008] The present invention takes into account that the relationship between the parameter items of the sample and the binding force may be linear or non-linear. Therefore, an SVR model is used to adapt to such data changes to construct a binding force prediction model. During the process of constructing the binding force prediction model, the present invention takes into account that the contribution degrees of different types of parameter items are different when obtaining the binding force of the sample. Based on this, the present invention obtains the weights of each parameter item by analyzing the importance of each parameter item compared to other parameter items. Using the weights of each parameter item of the sample to construct the model can effectively improve the accuracy of the predicted binding force value. On this basis, the present invention also takes into account that the volatility of each parameter item in the binding force test set will cause abnormal effects on the model construction. Based on this, the present invention calculates the corresponding penalty parameter through the volatility of each parameter item, thereby reducing the abnormal influence of the parameter item with stronger volatility on the model construction, improving the accuracy of the construction of the binding force prediction model, and effectively improving the accuracy of controlling the binding force adjustment of the strapping machine.

[0009] According to a method for adjusting the binding force of a strapping machine provided by the present invention, before the step of obtaining the parameter items corresponding to each sample in the binding force test set, it further includes: presetting the number of sample categories, and performing standard normalization processing on the volume data, weight data, and friction force data of each sample to obtain the binding force test set.

[0010] The present invention takes into account that the data value differences between different parameter items of the sample are relatively large, and the model construction may tend to the parameter item with a larger data value. Therefore, standard normalization processing is performed on the collected parameter data to prepare for the subsequent model construction.

[0011] A method for adjusting the tightening force of a bundling machine according to the present invention, obtaining the volume index of a sample by the difference between the volume of this sample and the volumes of other samples, and obtaining the weight index and frictional force index of this sample, includes: taking the cumulative sum of the differences between the volume of one sample and the volumes of other samples as the volume index of this sample; taking the cumulative sum of the differences between the weight of one sample and the weights of other samples as the weight index of this sample; taking the cumulative sum of the differences between the frictional force of one sample and the frictional forces of other samples as the frictional force index of this sample.

[0012] A method for adjusting the tightening force of a bundling machine according to the present invention, obtaining the volume weight of a sample according to the sum value of the sample volume index, weight index and frictional force index, and obtaining the weight weight and frictional force weight of this sample, includes: normalizing the ratio of the sample volume index to the sum value of the weight index and frictional force index to obtain the volume weight of this sample, and obtaining the weight weight and frictional force weight of this sample; normalizing the ratio of the sample weight index to the sum value of the volume index and frictional force index to obtain the weight weight of this sample; normalizing the ratio of the sample frictional force index to the sum value of the volume index and weight index to obtain the frictional force weight of this sample.

[0013] A method for adjusting the tightening force of a bundling machine according to the present invention, calculating the fluctuation index of this type of parameter item, includes: taking the negative of the cumulative sum of the absolute values of the differences between the weighted values of each sample parameter item and the weighted average as the exponent of the exponential function with base e to obtain the fluctuation index of this type of parameter item.

[0014] A method for adjusting the tightening force of a bundling machine according to the present invention, calculating the penalty parameter of the parameter item, includes: recording the difference between 1 and the fluctuation index of the parameter item as the penalty parameter of this type of parameter item.

[0015] The present invention considers that the greater the degree of fluctuation of a parameter item, the greater the possibility of causing an abnormal impact on the tightening force prediction model. Therefore, a smaller penalty parameter is set for the parameter item with a larger degree of fluctuation, so as to reduce the abnormal impact caused by the parameter item with a larger degree of fluctuation on the tightening force prediction model.

[0016] A method for adjusting the tightening force of a bundling machine according to the present invention, training a support vector regression model based on the tightening force of the sample, the weights of each parameter item and the penalty parameter, includes: weighting the parameter items based on the weights of each parameter item of the sample to obtain weighted parameters, taking the weighted parameters of each sample as a group of feature vectors to obtain the feature matrix of the tightening force test set; taking the tightening force of each sample as the target vector, and using the feature matrix, target vector and penalty parameter to train the SVR model to obtain the tightening force prediction model.

[0017] The binding force prediction model constructed by the present invention comprehensively considers the importance and fluctuation degree of each parameter item, calculates the weight and penalty parameter of the parameter item, and trains the binding force prediction model through the weighted result of the parameter item and the penalty parameter, which can effectively improve the accuracy of constructing the binding force prediction model.

[0018] According to a binding force adjustment method for a strapping machine provided by the present invention, training a support vector regression model based on the binding force of a sample, the weights of each parameter item, and the penalty parameter to achieve the binding force adjustment of the strapping machine includes: inputting each parameter item of the item to be strapped into the binding force prediction model to obtain the binding force required for the item to be strapped, and adjusting the binding force of the strapping machine based on the difference between the actual binding force of the strapping machine and the binding force required for the item to be strapped.

[0019] According to a binding force adjustment method for a strapping machine provided by the present invention, adjusting the binding force of the strapping machine based on the difference between the actual binding force of the strapping machine and the binding force required for the item to be strapped includes: generating a control signal based on the difference between the actual binding force of the strapping machine and the binding force required for the item to be strapped, and the tensioning component adjusts the packing belt based on the control signal to complete the strapping of the item to be strapped.

[0020] After obtaining the difference between the actual binding force of the strapping machine and the binding force required for the item to be strapped, the present invention can automatically generate a control signal to adjust the binding force according to the difference, reduce manual intervention, and effectively improve the item strapping efficiency.

[0021] In a second aspect, the present invention provides a binding force adjustment system for a strapping machine, adopting the following technical solution: A binding force adjustment system for a strapping machine includes: a processor and a memory, and the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the above-mentioned binding force adjustment method for a strapping machine is implemented.

[0022] By adopting the above technical solution, the above-mentioned binding force adjustment method for a strapping machine is generated into a computer program and stored in the memory to be loaded and executed by the processor, so as to manufacture a terminal device according to the memory and the processor, which is convenient to use.

[0023] The present invention has the following technical effects: Based on the above technical solution, for a method and system for adjusting the tightening force of a strapping machine provided by the present invention, when adjusting the tightening force of the strapping machine, an SVR prediction model is constructed through the relationship between the parameter items of the sample and the tightening force, and the tightening force of the strapping machine can be accurately controlled and adjusted based on the tightening force prediction result. In this process, the present invention takes into account that the contribution degrees of different types of parameter items are different when obtaining the tightening force of the sample; based on this, the present invention analyzes the importance degree of each parameter item compared with other parameter items to obtain the weight of each parameter item, and constructs a model using the weights of each parameter item of the sample, which can effectively improve the accuracy of the tightening force prediction value. On this basis, the present invention also takes into account the volatility of each parameter item in the tightening force test set. Based on this, the present invention calculates the corresponding penalty parameter through the volatility of each parameter item, so as to reduce the abnormal influence of the parameter item with stronger volatility on the model construction, improve the accuracy of the tightening force prediction model construction, and effectively improve the accuracy of controlling the adjustment of the tightening force of the strapping machine. Description of the Drawings

[0024] Figure 1 It is a schematic flowchart of a method for adjusting the tightening force of a strapping machine provided by an embodiment of the present invention. Detailed Embodiment

[0025] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention.

[0026] In order to ensure the bundling effect and quality of the articles, it is necessary to automatically adjust the tightening force of the strapping machine.

[0027] Based on this, an embodiment of the present invention discloses a method for adjusting the tightening force of a strapping machine. This method analyzes the relationship between the parameter items of the sample and the corresponding tightening force by training a Support Vector Regression (SVR) model, predicts the tightening force of the article to be strapped, and realizes the adjustment of the tightening force of the strapping machine, effectively improving the accuracy of the adjustment of the tightening force of the strapping machine.

[0028] Specifically, please refer to Figure 1 as shown in Figure 1 It is a schematic flowchart of a method for adjusting the tightening force of a strapping machine provided by an embodiment of the present invention, and this method specifically includes the following steps.

[0029] S1: Obtain the parameter items corresponding to each sample in the tightening force test set, and the parameter items include volume, weight, and friction.

[0030] It should be noted that larger items are more likely to be affected by external forces during transportation or storage, so greater binding force is required to maintain their stability. When heavy items are subjected to external forces, large inertial forces will be generated. If the binding force is small, sliding or detachment may occur during transportation. The greater the friction force on the surface of the item, the more difficult it is for the item to move relatively, so the effect of the binding force will be enhanced.

[0031] Based on this, the embodiments of the present invention analyze the relationships among the volume, weight, and friction force of the item and the binding force, construct a binding force prediction model to predict the binding force of the item to be strapped, and control the binding force of the strapping machine based on the predicted value of the binding force of the item to be strapped.

[0032] Exemplarily, in the embodiments of the present invention, before obtaining the parameter items corresponding to each sample in the binding force test set, it further includes: presetting the number of sample categories, and after performing standard normalization processing on the volume data, weight data, and friction force data of each sample, obtaining the binding force test set.

[0033] Among them, the number of sample categories can be preset to 300; the number of sample categories in the binding force test set and the number of samples in each category can be specifically set according to actual needs, and the embodiments of the present invention do not limit this too much here.

[0034] Exemplarily, after performing standard normalization processing on the volume data, weight data, and friction force data, missing data processing, etc. can also be performed, which can be specifically set according to actual needs.

[0035] It should be noted that based on the above steps, the parameter items corresponding to each sample can be obtained. However, when calculating the binding force of each type of sample, the contribution degrees of the parameter items to the binding force are different. The binding force of some samples is mainly determined by their volume, and some samples may depend on their weight, etc. Therefore, the relationship between the binding force and the parameter items of the sample may be a linear relationship or a non-linear relationship.

[0036] Based on this, the embodiments of the present invention obtain a binding force prediction model by training a support vector regression model, and comprehensively analyze the weights of the parameter items during the training process, so as to accurately obtain the predicted value of the binding force of the item to be strapped and realize the adjustment of the binding force of the strapping machine, that is, perform the following steps.

[0037] S2: Obtain the volume index of the sample through the difference between the volume of the sample and the volumes of other samples, and obtain the weight index and friction force index of the sample; normalize the ratio of the sample volume index to the sum of the weight index and friction force index to obtain the volume weight of the sample, and obtain the weight weight and friction force weight of the sample.

[0038] It should be noted that if the binding force test set is directly trained based on the support vector regression model without analyzing the weights of each parameter item, the obtained binding force prediction model will be more inclined to the relationship between the overall volume, weight, friction force and binding force of the samples, ignoring the relationship between the volume, weight, friction force and binding force of individual samples, resulting in different binding effects for different items during the subsequent binding force adjustment process.

[0039] Based on this, in the embodiment of the present invention, by analyzing the difference between one parameter item of each sample and other similar parameter items, the parameter index of this parameter item in the sample is obtained, and the weight of each parameter item in the sample is obtained through the ratio of one parameter index to the sum value of the other two parameter indexes.

[0040] Exemplarily, in the embodiment of the present invention, the volume index of the sample is obtained through the difference between the sample volume and other sample volumes, and the weight index and friction force index of the sample are obtained, including: taking the cumulative sum of the difference between one sample volume and other sample volumes as the volume index of the sample; taking the cumulative sum of the difference between one sample weight and other sample weights as the weight index of the sample; taking the cumulative sum of the difference between one sample friction force and other sample friction forces as the friction force index of the sample.

[0041] After obtaining each index based on the above steps, the weights of each item can be calculated.

[0042] Specifically, the volume weight of the sample is obtained according to the sum value of the sample volume index, weight index and friction force index.

[0043] Exemplarily, in the embodiment of the present invention, obtaining the weight weight and friction force weight of the sample includes: normalizing the ratio of the sample weight index to the sum value of the volume index and friction force index to obtain the weight weight of the sample; normalizing the ratio of the sample friction force index to the sum value of the volume index and weight index to obtain the friction force weight of the sample.

[0044] For the sake of easy understanding, the embodiment of the present invention takes calculating the volume weight of the sample as an example for illustration, but it does not mean that the embodiment of the present invention is only limited to this.

[0045] Exemplarily, to calculate the volume weight of the sample, the following relational expression can be specifically referred to: ; is the volume weight of the i-th sample, is the number of samples in the binding force test set, is the volume of the i-th sample, is the volume of the -th sample in the binding force test set except the i-th sample, is the weight of the i-th sample, is the weight of the -th sample in the strapping force test set except the i-th sample, is the frictional force of the i-th sample, is the frictional force of the -th sample in the strapping force test set except the i-th sample, is the standard normalization function.

[0046] In the above formula, represents the volume index of the i-th sample.

[0047] represents the weight index of the i-th sample.

[0048] represents the frictional force index of the i-th sample.

[0049] The larger the volume index of the i-th sample, the greater the difference between the volume of the i-th sample and the volumes of other samples; the larger the weight index of the i-th sample, the greater the difference between the weight of the i-th sample and the weights of other samples; the larger the frictional force index of the i-th sample, the greater the difference between the frictional force of the i-th sample and the frictional forces of other samples. If the ratio of the difference between the volume of the i-th sample and the volumes of other samples to the differences between its weight and frictional force and the weights and frictional forces of other samples is larger, it indicates that the i-th sample has a relatively large difference in volume compared to the remaining samples. Then, the possibility that the strapping force of the item needs to be adapted to the sample volume is greater, that is, the volume of the item needs to be emphasized during the strapping process. Therefore, the corresponding weight of the volume of the test item is larger.

[0050] Similarly, if the ratio of the difference between the weight of the i-th sample and the weights of other samples to the differences between its volume and frictional force and the volumes and frictional forces of other samples is larger, it indicates that the i-th sample has a relatively large difference in weight compared to the remaining samples. Then, the possibility that the strapping force of the item needs to be adapted to the sample weight is greater, that is, the weight of the item needs to be emphasized during the strapping process. Therefore, the corresponding weight of the weight of the test item is larger.

[0051] If the ratio of the difference between the frictional force of the i-th sample and the frictional forces of other samples to the differences between its weight and volume and the weights and volumes of other samples is larger, it indicates that the i-th sample has a relatively large difference in frictional force compared to the remaining samples. Then, the possibility that the strapping force of the item needs to be adapted to the sample frictional force is greater, that is, the frictional force of the item needs to be emphasized during the strapping process. Therefore, the corresponding weight of the frictional force of the test item is larger.

[0052] Similarly, the weight weight and friction weight of the sample can be obtained. After obtaining the weights of each parameter item of each sample based on the above steps, the following steps are continued.

[0053] S3: Obtain the weighted mean of each parameter item of the sample, and obtain the fluctuation index of this type of parameter item through the weighted value and weighted mean of each sample parameter item; calculate the penalty parameter of the parameter item, and the penalty parameter is negatively correlated with the fluctuation index of this type of parameter item.

[0054] It should be noted that based on the above steps to analyze the weights of each parameter item, the relationship between a single parameter item and the binding force can be emphasized during the training process of the SVR model. In addition, there will also be fluctuations in each parameter item itself in the binding force test set. Parameter items with large fluctuations may introduce noise or uncertainty during model training. During the training process of the SVR model, the larger the penalty parameter, the more the model tends to fit the training data, which may lead to overfitting; the smaller the penalty parameter, the simpler the model, and the generalization ability may be enhanced, but it may be underfitting.

[0055] Based on this, the embodiment of the present invention can adjust the penalty parameter of the parameter item in the SVR model based on the fluctuation degree of the parameter item. For parameter items with large fluctuations, the penalty parameter value can be reduced, so that the model can pay more attention to the key features that have an important impact on the prediction result, reduce the negative impact of parameter items with large fluctuations on model training, and thus improve the accuracy of model prediction.

[0056] Exemplarily, in the embodiment of the present invention, calculating the fluctuation index of the parameter item includes: taking the negative of the cumulative sum of the absolute values of the differences between the weighted values of each sample parameter item and the weighted mean as the exponent of the exponential function with e as the base to obtain the fluctuation index of this type of parameter item.

[0057] Among them, the product of the value of the sample parameter item and the corresponding weight is used as the weighted value of the sample parameter item; the mean value of the weighted values of the same type of parameter items of all samples is used as the weighted mean of this type of parameter item.

[0058] Exemplarily, in the embodiment of the present invention, calculating the penalty parameter of the parameter item includes: recording the difference between 1 and the fluctuation index of the parameter item as the penalty parameter of this type of parameter item.

[0059] Among them, if the parameter item is volume, the penalty parameter of volume can be obtained based on the above steps; if the parameter item is weight, the penalty parameter of weight can be obtained based on the above steps; if the parameter item is friction, the penalty parameter of friction can be obtained based on the above steps.

[0060] For the sake of easy understanding, the embodiment of the present invention takes calculating the penalty parameter of volume in the binding force test set as an example for illustration, but it does not mean that the embodiment of the present invention is only limited to this.

[0061] Exemplarily, the penalty parameter for calculating the volume can be specifically referred to the following relational expression: ; is the penalty parameter for the volume, is the number of samples in the strapping force test set, is the volume weight of the i-th sample, is the volume of the i-th sample, is the -th sample volume weight in the strapping force test set, is the -th sample volume in the strapping force test set, is the exponential function with base e, is the absolute value symbol.

[0062] In the above formula, is the weighted value of the volume of the i-th sample, is the -th sample volume weighted value, is the volume weighted mean in the strapping force test set.

[0063] represents the volume fluctuation index in the strapping force test set. The larger this value is, the greater the difference between the volume weighted value and the volume weighted mean in the strapping force test set, and the greater the fluctuation degree of the volume data. In order to reduce the negative impact of the volume data with large fluctuations on model training, it is necessary to reduce the penalty parameter, so the corresponding penalty parameter is also smaller.

[0064] Similarly, by analyzing the fluctuation conditions of the weight and friction force in the strapping force test set respectively, the penalty parameters of the weight and friction force can be accurately obtained, and the penalty parameters of each parameter item are used for training in the model.

[0065] S4: Train a support vector regression model based on the strapping force of the sample, the weights of each parameter item, and the penalty parameter to realize the adjustment of the strapping force of the strapping machine.

[0066] Exemplarily, in the embodiment of the present invention, training a support vector regression model based on the strapping force of the sample, the weights of each parameter item, and the penalty parameter includes: obtaining weighted parameters by weighting the parameter items based on the weights of each parameter item of the sample, using each weighted parameter of each sample as a group of feature vectors to obtain a feature matrix of the strapping force test set; using the strapping force of each sample as the target vector, and training the SVR model with the feature matrix, the target vector, and the penalty parameter to obtain a strapping force prediction model.

[0067] Among them, the kernel function in the SVR model can be a radial basis kernel function, which can be specifically set according to actual needs. The specific steps of training the SVR model through the feature matrix, target vector, and penalty parameter can be implemented by existing technologies, and will not be elaborated in the embodiments of the present invention.

[0068] Exemplarily, in the embodiments of the present invention, a support vector regression model is trained based on the tying force of the sample, the weights of each parameter item, and the penalty parameter to achieve the tying force adjustment of the strapping machine, including: inputting each parameter item of the item to be strapped into the tying force prediction model to obtain the tying force required for the item to be strapped, and adjusting the tying force of the strapping machine based on the difference between the actual tying force of the strapping machine and the tying force required for the item to be strapped.

[0069] Among them, the difference between the actual tying force of the strapping machine and the tying force required for the item to be strapped can be obtained by the difference between the actual tying force and the tying force required for the item to be strapped.

[0070] Exemplarily, in the embodiments of the present invention, adjusting the tying force of the strapping machine based on the difference between the actual tying force of the strapping machine and the tying force required for the item to be strapped includes: generating a control signal based on the difference between the actual tying force of the strapping machine and the tying force required for the item to be strapped, and the tightening component adjusts the packing strap based on the control signal to complete the strapping of the item to be strapped.

[0071] Among them, the step of the tightening component adjusting the packing strap based on the control signal can be implemented by a proportional-integral-derivative controller, and will not be elaborated in the embodiments of the present invention.

[0072] Exemplarily, in the embodiments of the present invention, after realizing the tying force adjustment of the strapping machine, it further includes: monitoring the strapping quality of the item after strapping.

[0073] Exemplarily, when monitoring the strapping quality of the item after strapping, a high-resolution industrial camera can be installed at the packing position of the strapping machine to collect images of the item after strapping to construct an item image set; manually annotate the shape of the strap and the corresponding defects in the item image set to obtain an item image set with annotations; input the item image set with annotations into a convolutional neural network for training to obtain a defect recognition model that can be used to identify strap defects.

[0074] Input the image of the item that has just been strapped into the defect recognition model to obtain the corresponding strapping quality monitoring result.

[0075] Among them, the specific steps of inputting the item image set with annotations into a convolutional neural network for training to obtain a defect recognition model that can be used to identify strap defects can be implemented by existing technologies, and will not be elaborated in the embodiments of the present invention.

[0076] It can be seen that in the embodiment of the present invention, when adjusting the tightening force of the strapping machine, the parameter items corresponding to each sample in the tightening force test set can be obtained. The parameter items include volume, weight, and friction force. The volume index of the sample is obtained through the difference between the volume of the sample and the volumes of other samples, and the weight index and friction force index of the sample are obtained. The volume weight of the sample is obtained according to the sum of the sample volume index, weight index, and friction force index, and the weight weight and friction force weight of the sample are obtained. The weighted average value of each parameter item of the sample is obtained, and the fluctuation index of this type of parameter item is calculated according to the weighted values and weighted average values of the parameter items of each sample. The penalty parameter of the parameter item is calculated, and the penalty parameter is negatively correlated with the fluctuation index of this type of parameter item. The support vector regression model is trained based on the tightening force of the sample, the weights of each parameter item, and the penalty parameter to realize the adjustment of the tightening force of the strapping machine, which can effectively improve the accuracy of the tightening force adjustment of the strapping machine.

[0077] The embodiment of the present invention also discloses a tightening force adjustment system for a strapping machine, including a processor and a memory. The memory stores computer program instructions, and when the computer program instructions are executed by the processor, a method for adjusting the tightening force of a strapping machine provided by the present invention is implemented.

[0078] The above system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface. Their settings and functions are known in the art, so they will not be elaborated here.

[0079] In the present invention, the foregoing memory can be any tangible medium that contains or stores a program, and this program can be used by or in combination with an instruction execution system, apparatus, or device.

[0080] The above are all preferred embodiments of the present invention. The protection scope of the present invention is not limited accordingly. Therefore, all equivalent changes made according to the structure, shape, and principle of the present invention should be covered within the protection scope of the present invention.

Claims

1. A method for adjusting the tightening force of a bundling machine, characterized in that, Including: Obtain the parameter items corresponding to each sample in the binding force test set, where the parameter items include volume, weight, and friction force; Obtain the volume index of the sample based on the difference between the sample volume and the volumes of other samples, and obtain the weight index and friction force index of the sample; Obtain the volume weight of the sample based on the sum value of the sample volume index, weight index, and friction force index, and obtain the weight weight and friction force weight of the sample; Obtain the weighted mean of each parameter item of the sample, and calculate the fluctuation index of this type of parameter item based on the weighted values and the weighted mean of the parameter items of each sample; Calculate the penalty parameter of the parameter item, where the penalty parameter is negatively correlated with the fluctuation index of this type of parameter item; Train a support vector regression model based on the binding force of the sample, the weights of each parameter item, and the penalty parameter to achieve the adjustment of the binding force of the strapping machine.

2. The method for adjusting the tightening force of a bundling machine according to claim 1, characterized in that, Before the step of obtaining the parameter items corresponding to each sample in the binding force test set, it further includes: Preset the number of sample categories, and after performing standard normalization processing on the volume data, weight data, and friction force data of each sample, obtain the binding force test set.

3. A method for adjusting the tightening force of a banding machine according to claim 1, characterized in that, The step of obtaining the volume index of the sample based on the difference between the sample volume and the volumes of other samples, and obtaining the weight index and friction force index of the sample includes: Take the cumulative sum of the differences between the volume of one sample and the volumes of other samples as the volume index of the sample; take the cumulative sum of the differences between the weight of one sample and the weights of other samples as the weight index of the sample; take the cumulative sum of the differences between the friction force of one sample and the friction forces of other samples as the friction force index of the sample.

4. A method for adjusting the tightening force of a belt tying machine according to claim 1, characterized in that, The step of obtaining the volume weight of the sample based on the sum value of the sample volume index, weight index, and friction force index, and obtaining the weight weight and friction force weight of the sample includes: Normalize the ratio of the sample volume index to the sum value of the weight index and friction force index to obtain the volume weight of the sample, and obtain the weight weight and friction force weight of the sample; normalize the ratio of the sample weight index to the sum value of the volume index and friction force index to obtain the weight weight of the sample; normalize the ratio of the sample friction force index to the sum value of the volume index and weight index to obtain the friction force weight of the sample.

5. A method for adjusting the tightening force of a banding machine according to claim 1, characterized in that, The step of calculating the fluctuation index of this type of parameter item includes: Take the negative of the cumulative sum of the absolute values of the differences between the weighted values and the weighted mean of the parameter items of each sample as the exponent of the exponential function with base e to obtain the fluctuation index of this type of parameter item.

6. The method for adjusting the tightening force of a bundling machine according to claim 1, characterized in that The step of calculating the penalty parameter of the parameter item includes: Record the difference between 1 and the fluctuation index of the parameter item as the penalty parameter of this type of parameter item.

7. A method for adjusting the tightening force of a bundling machine according to claim 1, characterized in that, The step of training a support vector regression model based on the binding force of the sample, the weights of each parameter item, and the penalty parameter includes: Perform weighting on the parameter items based on the weights of each parameter item of the sample to obtain weighted parameters, take the weighted parameters of each sample as a group of feature vectors to obtain the feature matrix of the binding force test set; take the binding force of each sample as the target vector, and use the feature matrix, target vector, and penalty parameter to train the SVR model to obtain the binding force prediction model.

8. A method for adjusting the tightening force of a banding machine according to claim 7, characterized in that, The step of training a support vector regression model based on the binding force of the sample, the weights of each parameter item, and the penalty parameter to achieve the adjustment of the binding force of the strapping machine includes: Input each parameter item of the item to be strapped into the strapping force prediction model to obtain the required strapping force of the item to be strapped, and adjust the strapping force of the strapping machine based on the difference between the actual strapping force of the strapping machine and the required strapping force of the item to be strapped.

9. A method for adjusting the tightening force of a banding machine according to claim 8, characterized in that, The adjusting the strapping force of the strapping machine based on the difference between the actual strapping force of the strapping machine and the required strapping force of the item to be strapped includes: Generating a control signal based on the difference between the actual strapping force of the strapping machine and the required strapping force of the item to be strapped, and the tensioning component adjusts the packing tape based on the control signal to complete the strapping of the item to be strapped.

10. A tightening force adjustment system for a banding machine, characterized in that, Includes: A processor and a memory, the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the method for adjusting the strapping force of a strapping machine according to any one of claims 1-9 is implemented.

Images