Method and System for Determining the Mass of Goods Loaded by a Warehousing Robot

Abstract

The present invention discloses a method and system for determining the mass of goods carried by a warehousing robot, comprising the following steps: training a model of the quality evaluation of warehousing goods by using a BP neural network for the quality damage category and degree of the warehousing sample and the quality characterization parameters of the warehousing sample; obtaining the quality characterization parameters of the goods carried by the warehousing robot, and using the quality evaluation model to obtain the quality damage category and degree of the goods carried by the warehousing robot based on the quality characterization parameters of the goods carried by the warehousing robot. The present invention constructs a quality evaluation model to realize the quality evaluation of the goods carried by the warehousing robot during the process of transporting goods by the warehousing robot, and further realizes the identification of the goods with quality damage, as well as the damage category and degree of the goods during the handling process, facilitating subsequent personnel to master the sorting situation and avoiding the ineffective handling of transporting damaged items into the warehouse.

Description

Technical Field

[0001] The present invention relates to the technical field of warehousing logistics, and particularly relates to a method and system for determining the quality of goods carried by a warehousing robot. Background Art

[0002] Warehousing logistics is to utilize self-built or leased warehouses, sites for storing, preserving, loading, unloading and transporting, and distributing goods. The traditional definition of warehousing is given from the perspective of material reserves. Modern "warehousing" is not the traditional "warehouse" or "warehouse management", but warehousing under the background of economic globalization and supply chain integration, which is warehousing in a modern logistics system. A warehousing logistics robot refers to a robot used for handling operations of goods in and out of the warehouse in indoor environments such as logistics warehouses and production warehouses. Therefore, warehousing logistics robots play an important role in warehousing logistics.

[0003] The existing technology mainly uses warehousing robots for handling operations, but it is unable to identify the quality of the handled goods, resulting in undifferentiated handling of goods with damaged quality and goods without damaged quality, and further quality screening is still required after handling into the warehouse, causing ineffective handling of goods and poor handling effects. Summary of the Invention

[0004] The purpose of the present invention is to provide a method and system for determining the quality of goods carried by a warehousing robot to solve the technical problem of undifferentiated handling and poor handling effects in the existing technology.

[0005] To solve the above technical problems, the present invention specifically provides the following technical solutions:

[0006] A method for determining the quality of goods carried by a warehousing robot includes the following steps:

[0007] Step S1: Obtain a warehousing sample by mixing multiple groups of warehousing goods with quality damage and a group of warehousing goods without quality damage, and place the warehousing sample in an empty warehousing robot to obtain quality characterization parameters of the warehousing sample. The quality characterization parameters include goods weight, goods noise, and goods temperature and humidity;

[0008] Step S2: Use a BP neural network to train the quality damage category and degree of the warehousing sample and the quality characterization parameters of the warehousing sample to obtain a quality evaluation model for warehousing goods;

[0009] Step S3: Obtain the mass characterization parameters of the goods carried by the warehousing robot, and use the mass evaluation model to obtain the mass damage category and degree of the goods carried by the warehousing robot based on the mass characterization parameters of the goods carried by the warehousing robot, so as to realize the mass evaluation of the goods carried by the warehousing robot during the transportation process.

[0010] As a preferred solution of the present invention, the obtaining of multiple groups of warehousing goods with quality damage includes:

[0011] Collect all the warehousing goods with quality damage, classify the quality damage categories of the warehousing goods with quality damage, and count the number of warehousing goods included in each quality damage category;

[0012] Set the selection ratio of the quantity of goods for each quality damage category according to the quantity of warehousing goods. The formula for setting the selection ratio is:

[0013] [L 1 :L 2 :L 3 :,,,:L N =[A 1 :A 2 :A 3 :,,,:A N ;

[0014] In the formula, L 1 , L 2 , L 3 , L N respectively represent the selection ratios of the quantity of goods for the 1st, 2nd, 3rd, and Nth quality damage categories, and A 1 , A 2 , A 3 , A N respectively represent the quantities of warehousing goods for the 1st, 2nd, 3rd, and Nth quality damage categories;

[0015] Set the total selection quantity, sequentially obtain the selection quantities of warehousing goods in each quality damage category according to the selection ratio of the quantity of goods, and randomly select warehousing goods in each quality damage category according to the selection quantity to obtain multiple groups of warehousing goods with quality damage belonging to each quality damage category. The formula for calculating the selection quantity is:

[0016]

[0017] In the formula, n i is the selection quantity of warehousing goods in the i-th quality damage category, L i is the selection ratio of the quantity of goods in the i-th quality damage category, i is a measurement constant, and N is the total number of quality damage categories.

[0018] As a preferred embodiment of the present invention, 1 / N of the total quantity is selected as the quantity of the warehoused goods without quality damage to obtain a group of warehoused goods without quality damage.

[0019] As a preferred embodiment of the present invention, placing the warehousing sample in an empty warehousing robot to obtain the quality characterization parameters of the warehousing sample includes:

[0020] The built-in sensing sensor component in the warehousing robot obtains the weight, noise, temperature and humidity of each warehousing sample, and the weight, noise, temperature and humidity of each warehousing sample constitute the quality characterization parameters of each warehousing sample.

[0021] As a preferred embodiment of the present invention, the construction of the quality evaluation model includes:

[0022] Taking the quality characterization parameters of the warehousing sample as the input items of the BP neural network, taking the quality damage category and degree of quality damage to which the warehousing sample belongs as the output items of the BP neural network, and using the BP neural network to perform model training in the input items and the output items to obtain the quality evaluation model;

[0023] The function expression of the quality evaluation model is:

[0024] [K, P]=BP(S);

[0025] In the formula, K is the function identifier of the quality damage category, P is the function identifier of the degree of quality damage, S is the function identifier of the quality characterization parameter, and BP is the function identifier of the BP neural network.

[0026] As a preferred embodiment of the present invention, obtaining the quality characterization parameters of the goods loaded by the warehousing robot includes:

[0027] The built-in sensing sensor component in the warehousing robot obtains the weight, noise, temperature and humidity of the goods loaded by the warehousing robot, and the weight, noise, temperature and humidity of the goods loaded by the warehousing robot constitute the quality characterization parameters of the goods loaded by the warehousing robot.

[0028] As a preferred embodiment of the present invention, obtaining the quality damage category and degree of quality damage of the goods loaded by the warehousing robot includes:

[0029] Inputting the quality characterization parameters of the goods loaded by the warehousing robot into the quality evaluation model, and the quality evaluation model outputs the quality damage category and degree of quality damage of the goods loaded by the warehousing robot.

[0030] As a preferred solution of the present invention, the cargo weight, cargo noise, and cargo temperature and humidity are normalized before constituting the quality characterization parameters.

[0031] As a preferred solution of the present invention, the quantification of the degree of quality damage includes:

[0032] The quality characterization parameters of each storage sample in each quality damage category are obtained, and the difference between the quality characterization parameters of the storage samples and the quality characterization parameters of the storage goods without quality damage is calculated to obtain the quality damage degree of each storage sample in the quality damage category to which it belongs. The calculation formula of the quality damage degree is:

[0033]

[0034] In the formula, M is the quantity of stored goods without quality damage, P i,j is the quality damage degree of the jth storage sample in the i-th quality damage category, S i,j is the quality characterization parameter of the jth storage sample in the i-th quality damage category, S r is the quality characterization parameter of the rth stored goods that have not suffered quality damage, and j, r is the measurement constant.

[0035] As a preferred embodiment of the present invention, the present invention provides a system for determining the quality of goods carried by the warehouse robot according to the method for determining the quality of goods carried by the warehouse robot, comprising: a perception sensor component and a data processor, the perception sensor component comprising a weight detection sensor, a noise detection sensor and a temperature and humidity detection sensor, the perception sensor component is built into the lifting mechanism of the warehouse robot, the data processor is built with the quality assessment model, the perception sensor component is communicatively connected with the data processor to input the quality characterization parameters of the goods carried by the warehouse robot into the quality assessment model to obtain the quality damage category and quality damage degree of the goods carried by the warehouse robot.

[0036] Compared with the prior art, the present invention has the following beneficial effects:

[0037] The present invention constructs a quality assessment model to realize quality assessment of the goods carried by the storage robot during the process of the storage robot carrying goods, and then realizes the identification of goods with quality damage, as well as the type and degree of damage of the goods during the transportation process, so as to facilitate subsequent personnel to grasp the sorting situation and avoid ineffective transportation of damaged items into the warehouse. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only exemplary. For those of ordinary skill in the art, without creative efforts, other implementation drawings can also be obtained according to the provided drawings.

[0039] Figure 1 Flowchart of the method for determining the mass of the goods carried by the warehousing robot provided by the embodiment of the present invention;

[0040] Figure 2 Block diagram of the determination system provided by the embodiment of the present invention.

[0041] The reference numerals in the figure are respectively represented as follows:

[0042] 1 - Sensing sensor assembly; 2 - Data processor. Specific implementation mode

[0043] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the protection scope of the present invention.

[0044] As Figure 1 shown, the present invention provides a method for determining the mass of the goods carried by a warehousing robot, including the following steps:

[0045] Step S1, obtain a warehousing sample by mixing multiple groups of warehousing goods with quality damage and a group of warehousing goods without quality damage, and place the warehousing sample in an empty warehousing robot to obtain the quality characterization parameters of the warehousing sample. The quality characterization parameters include the weight of the goods, the noise of the goods, and the temperature and humidity of the goods;

[0046] Obtaining multiple groups of warehousing goods with quality damage includes:

[0047] Collect all the warehousing goods with quality damage, classify the quality damage categories of the warehousing goods with quality damage, and count the number of warehousing goods included in each quality damage category;

[0048] Set the selection ratio of the number of goods for each quality damage category according to the number of warehousing goods. The formula for setting the selection ratio is:

[0049] [L 1 :L 2 :L 3 :,,,:LN =[A 1 :A 2 :A 3 :,,, :A N ;

[0050] Wherein, L 1 , L 2 , L 3 , L N respectively represent the selection ratios of the quantities of goods in the 1st, 2nd, 3rd, and Nth quality damage categories, A 1 , A 2 , A 3 , A N respectively represent the quantities of warehoused goods in the 1st, 2nd, 3rd, and Nth quality damage categories;

[0051] Set the total selection quantity, and successively obtain the selection quantities of the warehoused goods in each quality damage category according to the selection ratios of the quantities of goods, and randomly select the warehoused goods in each quality damage category according to the selection quantities to obtain multiple groups of warehoused goods with quality damage belonging to each quality damage category. The calculation formula for the selection quantity is:

[0052]

[0053] Wherein, n i is the selection quantity of the warehoused goods in the ith quality damage category, L i is the selection ratio of the quantity of goods in the ith quality damage category, i is a measurement constant, and N is the total number of quality damage categories.

[0054] Perform a proportional analysis among the quality damage categories for all the warehoused goods with quality damage. Among them, the higher the proportion of a quality damage category, the higher the quality damage incidence rate corresponding to this quality damage category; the lower the proportion of a quality damage category, the lower the quality damage incidence rate corresponding to this quality damage category. Therefore, when selecting samples, the selection is still carried out according to the proportion of the quality damage categories, so as to select more warehoused goods in the quality damage categories with a high incidence rate to ensure the data richness of this quality damage category, and further enable the model to learn more features of this quality damage category during model training, improve the fitting accuracy and prediction efficiency of the quality assessment model for this quality damage category, realize that the quality damage incidence rate is proportional to the fitting accuracy and prediction efficiency of the quality assessment model, improve the model universality, and be more in line with the actual scenario usage.

[0055] Take 1 / N of the total selection quantity as the selection quantity of the warehoused goods without quality damage to obtain a group of warehoused goods without quality damage.

[0056] Place the storage sample in an empty storage robot to obtain the quality characterization parameters of the storage sample, including:

[0057] The built-in perception sensor component in the storage robot obtains the cargo weight, cargo noise, cargo temperature and humidity of each storage sample, and the cargo weight, cargo noise, cargo temperature and humidity of each storage sample constitute the quality characterization parameters of each storage sample. The quality characterization parameters can be added, deleted and modified as needed during actual use.

[0058] Step S2, using the BP neural network to train the quality damage category and quality damage degree of the storage samples and the quality characterization parameters of the storage samples to obtain a quality assessment model for the storage goods;

[0059] The construction of the quality assessment model includes:

[0060] The quality characterization parameters of the storage samples are used as the input items of the BP neural network, the quality damage category and quality damage degree of the storage samples are used as the output items of the BP neural network, and the BP neural network is used to train the model in the input items and output items to obtain the quality assessment model;

[0061] The function expression of the quality assessment model is:

[0062] [K,P]=BP(S);

[0063] Where K is the function identifier of the quality damage category, P is the function identifier of the quality damage degree, S is the function identifier of the quality characterization parameter, and BP is the function identifier of the BP neural network.

[0064] Quantification of quality damage includes:

[0065] The quality characterization parameters of each storage sample in each quality damage category are obtained, and the difference between the quality characterization parameters of the storage samples and the quality characterization parameters of the storage goods without quality damage is calculated to obtain the quality damage degree of each storage sample in the quality damage category to which it belongs. The calculation formula for the quality damage degree is:

[0066]

[0067] In the formula, M is the quantity of stored goods without quality damage, P i,j is the quality damage degree of the jth storage sample in the i-th quality damage category, S i,j is the quality characterization parameter of the jth storage sample in the i-th quality damage category, S r is the quality characterization parameter of the rth stored goods that have not suffered quality damage, and j, r is the measurement constant.

[0068] The degree of quality damage is the sum of the Euclidean distances between the warehoused goods with quality damage and all the warehoused goods without quality damage. The larger the sum of the Euclidean distances, the farther the warehoused goods with quality damage are from all the warehoused goods without quality damage, the lower the similarity, and the higher the degree of quality damage of the warehoused goods with quality damage. The smaller the sum of the Euclidean distances, the closer the warehoused goods with quality damage are to all the warehoused goods without quality damage, the higher the similarity, and the lower the degree of quality damage of the warehoused goods with quality damage.

[0069] By constructing a quality assessment model, the mapping between quality characterization parameters, quality damage categories, and the degree of quality damage is realized. Thus, the quality damage situation of the goods can be directly known through the obtained quality characterization parameters. For example, if the quality damage category of goods A obtained through the quality assessment model is category 1 and the damage degree is P, feedback is given to the operator and waiting for the operator's handling.

[0070] The entire process of quality assessment is fully automated. Only the quality characterization parameters need to be obtained, and then the model outputs. There is no need for manual evaluation by personnel, which improves efficiency. Moreover, quality assessment can be synchronously solved during the transportation process. If there is no quality damage, it is directly carried into the warehouse. However, if quality damage occurs, it will be feedback to the operator for subsequent processing, which can ensure that the quality of the goods carried into the warehouse is good and no ineffective handling occurs.

[0071] Step S3: Obtain the quality characterization parameters of the goods carried by the warehousing robot, and use the quality assessment model to obtain the quality damage category and the degree of quality damage of the goods carried by the warehousing robot based on the quality characterization parameters of the goods carried by the warehousing robot, so as to realize the quality assessment of the goods carried by the warehousing robot during the transportation process.

[0072] Obtaining the quality characterization parameters of the goods carried by the warehousing robot includes:

[0073] The built-in sensing sensor component in the warehousing robot obtains the weight, noise, temperature, and humidity of the goods carried by the warehousing robot, and the weight, noise, temperature, and humidity of the goods carried by the warehousing robot constitute the quality characterization parameters of the goods carried by the warehousing robot.

[0074] Obtaining the quality damage category and the degree of quality damage of the goods carried by the warehousing robot includes:

[0075] Input the quality characterization parameters of the goods carried by the warehousing robot into the quality assessment model, and the quality assessment model outputs the quality damage category and the degree of quality damage of the goods carried by the warehousing robot.

[0076] The weight, noise, temperature, and humidity of the goods are normalized before being used as quality characterization parameters.

[0077] As Figure 2 shown, based on the method for determining the mass of the goods carried by the above-mentioned warehousing robot, the present invention provides a determination system, including: a sensing sensor assembly 1 and a data processor 2. The sensing sensor assembly includes a weight detection sensor, a noise detection sensor, and a temperature and humidity detection sensor. The sensing sensor assembly is built into the lifting mechanism of the warehousing robot. A quality evaluation model is built into the data processor. The sensing sensor assembly is communicatively connected to the data processor to input the quality characterization parameters of the goods carried by the warehousing robot into the quality evaluation model to obtain the quality damage category and degree of the goods carried by the warehousing robot.

[0078] The present invention constructs a quality evaluation model to realize the quality evaluation of the goods carried by the warehousing robot during the process of transporting the goods by the warehousing robot, and further realizes the identification of the goods with quality damage, as well as the damage category and degree of the goods during the handling process, which is convenient for subsequent personnel to master the sorting situation and avoid the ineffective handling of transporting damaged items into the warehouse.

[0079] The above embodiments are only exemplary embodiments of the present application and are not used to limit the present application. The protection scope of the present application is defined by the claims. Those skilled in the art can make various modifications or equivalent replacements within the essence and protection scope of the present application, and such modifications or equivalent replacements should also be regarded as falling within the protection scope of the present application.

Claims

1. A method for determining the mass of goods carried by a warehousing robot, characterized in that, it includes the following steps: Step S1: Obtain a warehousing sample by mixing multiple groups of warehousing goods with quality damage and a group of warehousing goods without quality damage, and place the warehousing sample in an empty warehousing robot to obtain the quality characterization parameters of the warehousing sample. The quality characterization parameters include the weight of the goods, the noise of the goods, and the temperature and humidity of the goods; Step S2: Use a BP neural network to train the quality damage category and degree of the warehousing sample and the quality characterization parameters of the warehousing sample to obtain a quality evaluation model for the warehousing goods; Step S3: Obtain the quality characterization parameters of the goods carried by the warehousing robot, and use the quality evaluation model to obtain the quality damage category and degree of the goods carried by the warehousing robot based on the quality characterization parameters of the goods carried by the warehousing robot, so as to realize the quality evaluation of the goods carried by the warehousing robot during the transportation process; The obtaining of multiple groups of warehousing goods with quality damage includes: Collect all warehousing goods with quality damage, classify the quality damage categories of the warehousing goods with quality damage, and count the number of warehousing goods included in each quality damage category; Set the selection ratio of the quantity of goods for each quality damage category according to the quantity of warehousing goods. The formula for setting the selection ratio is: [L 1 :L 2 :L 3 :,,,:L N = [A 1 :A 2 :A 3 :,,,:A N ; Wherein, L 1 , L 2 , L 3 , L N respectively represent the selection ratios of the quantities of goods in the 1st, 2nd, 3rd, and Nth quality damage categories, A 1 , A 2 , A 3 , A N respectively represent the quantities of warehoused goods in the 1st, 2nd, 3rd, and Nth quality damage categories; Set the total selection quantity, and successively obtain the selection quantity of warehousing goods in each quality damage category according to the selection ratio of the quantity of goods. Randomly select warehousing goods in each quality damage category according to the selection quantity to obtain multiple groups of warehousing goods with quality damage belonging to each quality damage category. The formula for calculating the selection quantity is: Where n i is the selected quantity of the stored goods in the i-th quality damage category, L i is the proportion of the quantity of goods selected in the i-th quality damage category, i is a measurement constant, and N is the total number of quality damage categories; The construction of the quality evaluation model includes: Use the quality characterization parameters of the warehousing sample as the input items of the BP neural network, and use the quality damage category and degree of the warehousing sample as the output items of the BP neural network. Use the BP neural network to train the model in the input items and the output items to obtain the quality evaluation model; The function expression of the quality evaluation model is: [K, P] = BP(S); In the formula, K is the function identifier of the quality damage category, P is the function identifier of the quality damage degree, S is the function identifier of the quality characterization parameters, and BP is the function identifier of the BP neural network.

2. A method for determining the mass of goods carried by a warehousing robot according to claim 1, characterized in that: Take 1 / N of the total selection quantity as the selection quantity of the warehousing goods without quality damage to obtain a group of warehousing goods without quality damage.

3. A method for determining the mass of goods carried by a warehousing robot according to claim 2, characterized in that: The obtaining of the quality characterization parameters of the warehousing sample by placing the warehousing sample in an empty warehousing robot includes: The built-in sensing sensor component in the warehousing robot obtains the weight of the goods, the noise of the goods, and the temperature and humidity of the goods for each warehousing sample, and the weight of the goods, the noise of the goods, and the temperature and humidity of each warehousing sample constitute the quality characterization parameters of each warehousing sample.

4. A method for determining the mass of goods loaded by a storage robot according to claim 3, Features: The obtaining of the quality characterization parameters of the goods loaded by the storage robot includes: The built-in perception sensor component in the storage robot acquires the weight, noise, temperature and humidity of the goods carried by the storage robot, and the weight, noise and temperature and humidity of the goods carried by the storage robot constitute the quality characterization parameters of the goods carried by the storage robot.

5. A method for determining the mass of goods loaded by a storage robot according to claim 4, Features: The quality damage category and quality damage degree of the goods loaded by the storage robot are obtained by: The quality characterization parameters of the goods carried by the storage robot are input into the quality assessment model, and the quality assessment model outputs the quality damage category and quality damage degree of the goods carried by the storage robot.

6. A method for determining the mass of goods loaded by a storage robot according to claim 5, It is characterized in that The cargo weight, cargo noise, and cargo temperature and humidity are normalized before forming the quality characterization parameters.

7. A method for determining the mass of goods loaded by a storage robot according to claim 6, It is characterized in that The quantification of the degree of quality damage includes: The quality characterization parameters of each storage sample in each quality damage category are obtained, and the difference between the quality characterization parameters of the storage samples and the quality characterization parameters of the storage goods without quality damage is calculated to obtain the quality damage degree of each storage sample in the quality damage category to which it belongs. The calculation formula of the quality damage degree is: Wherein, M is the quantity of warehoused goods without quality damage, P i,j is the degree of quality damage of the j-th warehousing sample in the i-th quality damage category, S i,j is the quality characterization parameter of the j-th warehousing sample in the i-th quality damage category, S r is the quality characterization parameter of the r-th warehoused goods without quality damage, and j and r are measurement constants.

8. A system for determining the mass of goods carried by a storage robot according to any one of claims 1 to 7, It is characterized in that include: A perception sensor component and a data processor, wherein the perception sensor component includes a weight detection sensor, a noise detection sensor, and a temperature and humidity detection sensor. The perception sensor component is built into the lifting mechanism of the warehouse robot, and the data processor is built with the quality assessment model. The perception sensor component is communicatively connected with the data processor to input the quality characterization parameters of the goods carried by the warehouse robot into the quality assessment model to obtain the quality damage category and quality damage degree of the goods carried by the warehouse robot.

Images