A digital smart factory production management method based on blockchain

Abstract

The present invention relates to the technical field of intelligent factory production management, and specifically discloses a digital intelligent factory production management method based on blockchain, wherein a camera is arranged at a product drop port of a target production device to collect images of each workpiece in the same batch corresponding to the target production device, and determine the quality score of each workpiece in the same batch corresponding to the target production device; evaluate the production status evaluation coefficient of the target production device, and then derive the production efficiency of the target production device; finally, calculate the number of workpieces assigned to the target production device corresponding to each production task, and feed back the number of workpieces assigned to the target production device corresponding to each production task to the equipment control terminal, which performs corresponding processing on the target production equipment, can timely discover potential performance fluctuations or failures of the equipment, and ensure that the equipment operates in the best state; at the same time, dynamically adjust the allocation of production tasks based on the production efficiency of the equipment, and optimize resource utilization.

Description

Technical Field

[0001] The present invention belongs to the technical field of smart factory production management and relates to a digital smart factory production management method based on blockchain. Background Art

[0002] With the advancement of Industry 4.0, smart factories have gradually become an important development direction of the manufacturing industry. The purpose of realizing intelligent production management in factories is to improve production efficiency, reduce operating costs, improve product quality, and enhance the ability to respond to changes in market demand. By introducing advanced automation technology, data analysis and artificial intelligence, factories can achieve real-time monitoring of the production process and adaptive adjustment of the production process, thereby reducing manual intervention and errors and improving production flexibility and sustainability.

[0003] Current technologies for the allocation of production tasks mainly focus on optimizing production efficiency, rationally allocating resources, and maximizing equipment utilization, and usually make dynamic adjustments by real-time monitoring of production progress, equipment status, and resource consumption. However, these allocation methods still have some defects and disadvantages. For example, over-reliance on historical data and rule algorithms may not be able to fully respond to emergencies or complex changes in the production environment; in addition, the allocation system often lacks comprehensive consideration of multi-dimensional factors (equipment health status, etc.), resulting in a lack of flexibility and accuracy in the allocation plan, which in turn affects the overall production efficiency and response speed. Summary of the invention

[0004] In view of the above problems existing in the prior art, the present invention provides a digital smart factory production management method based on blockchain to solve the above technical problems.

[0005] In order to achieve the above purpose and other purposes, the technical solution adopted by the present invention is as follows:

[0006] The first aspect of the present invention provides a digital smart factory production management method based on blockchain, the method comprising the following steps:

[0007] A camera is arranged at the product drop port of the target production equipment to collect images of each workpiece in the same batch of the target production equipment, so as to determine the quality score of each workpiece in the same batch of the target production equipment;

[0008] Based on the quality score of each workpiece in the same batch of the target production equipment, the production status evaluation coefficient of the target production equipment is reversely evaluated, and then the production efficiency of the target production equipment is derived;

[0009] The number of workpieces assigned to the target production equipment for each production task is calculated based on production efficiency, and the number of workpieces assigned to the target production equipment for each production task is fed back to the equipment control terminal, which then performs corresponding processing on the target production equipment.

[0010] In a preferred technical solution of the present application, a camera is arranged at the product drop port of the target production equipment, and specific arrangement parameters include the arrangement position and the arrangement pitch angle.

[0011] In the preferred technical solution of the present application, the layout position of the camera corresponding to the product drop opening of the target production equipment is determined, and the specific determination process is as follows:

[0012] Based on the standard size range of the standard workpiece, the maximum width W and the maximum height H of the workpiece are extracted;

[0013] And obtain the type of the corresponding camera to be deployed, based on which the horizontal field of view angle θ of the camera is obtained 水平 and vertical field angle θ 垂直 ;

[0014] This determines the minimum installation distance between the camera and the product drop point

[0015]

[0016] Obtain the opening direction corresponding to the product drop port, take the product drop point as the center point, make a horizontal extension line to the opening direction corresponding to the product drop port, set the distance of the horizontal extension line to the minimum installation distance, and make a vertical extension line with the end point of the horizontal extension line, obtain the height point where the height of the vertical extension line is consistent with the height of the product drop port as the layout position of the camera at the product drop port of the target production equipment.

[0017] In the preferred technical solution of the present application, the pitch angle of the camera at the target production equipment corresponding to the product drop opening is determined, and the specific determination process is as follows:

[0018] By calculating the formula Calculate the pitch angle θ′ of the camera at the product drop opening of the target production equipment, H 布设 The height of the product drop opening.

[0019] In the preferred technical solution of this application, the process of determining the quality score of each workpiece in the same batch corresponding to the target production equipment is as follows:

[0020] The convolutional neural network model is used to detect the images of each workpiece corresponding to the target production equipment to obtain the defect features of each workpiece corresponding to the target production equipment; the size features of each workpiece corresponding to the target production equipment are measured by image processing technology; the color features of each workpiece corresponding to the target production equipment are analyzed by color space conversion; the above defect features, size features and color features are combined into a feature vector I corresponding to each workpiece of the target production equipment i , i is the number of each workpiece, i = 1, 2, ... N, N is the total number of workpieces in the same batch;

[0021] Obtain the standard feature vector I′ of the workpiece corresponding to the target production equipment. For each workpiece i, calculate the similarity between its feature vector and the standard feature vector. || || is the norm symbol;

[0022] Based on the similarity between the feature vector of each workpiece corresponding to the target production equipment and the standard feature vector, the quality score of each workpiece corresponding to the target production equipment is obtained. α is the similarity threshold.

[0023] In the preferred technical solution of this application, the production status evaluation coefficient of the target production equipment is evaluated, and the specific evaluation process is as follows:

[0024] Average quality score of products in the same batch based on the target production equipment And the standard deviation of the quality scores of the target production equipment corresponding to the workpieces in the same batch Comprehensively define the volatility coefficient ε of the target production equipment corresponding to the same batch of workpieces;

[0025] Then use the calculation formula The production status evaluation coefficient ZT of the target production equipment is evaluated, where α3 is a predefined weight factor used to adjust the relative importance of the average quality score and volatility of the equipment, and Q' represents the benchmark quality score of the production equipment under ideal conditions.

[0026] In the preferred technical solution of the present application, the volatility coefficient ε of the target production equipment corresponding to the same batch of workpieces is comprehensively defined, and the specific definition process is:

[0027] The inclination is introduced to reflect the distribution of the workpiece quality score. The calculation formula for the inclination of the quality score of the same batch of workpieces of the specific target production equipment is as follows:

[0028] QX is the quality score inclination of the target production equipment corresponding to the same batch of workpieces;

[0029] The design target production equipment corresponds to the initial volatility coefficient of the same batch of workpieces. The specific formula is shown as follows:

[0030]

[0031] Where e is a natural constant, α1 is the preset sensitivity threshold of control volatility to device status, σ0 is the predefined volatility threshold, and when σ Q =σ0, ε1=0.5, indicating that the target production equipment is in a critical state. Q <σ0, ε1 approaches 1, indicating that the target production equipment has a small volatility and the equipment state is stable. Q >σ0, ε1 approaches 0, indicating that the target production equipment has large volatility and the equipment status is unstable;

[0032] The initial volatility coefficient of the target production equipment corresponding to the same batch of workpieces is combined with the quality score inclination of the target production equipment corresponding to the same batch of workpieces, and the volatility coefficient ε=ε1×(1-α2×|QX|) of the target production equipment corresponding to the same batch of workpieces is obtained comprehensively, where α2 is the preset influence value of the control inclination on the volatility coefficient. The larger the inclination, the smaller the volatility coefficient value.

[0033] In a preferred technical solution of the present application, the production efficiency of the target production equipment is derived, and the specific derivation process includes the following steps:

[0034] Based on the quality score of each workpiece in the same batch corresponding to the target production equipment, it is compared with a predefined quality score threshold, each workpiece with a quality score greater than the predefined quality score threshold is counted as a qualified workpiece, the total number of qualified workpieces is counted, and the ratio operation is performed on it with the total number of workpieces in the same batch to obtain the production yield of the target production equipment in the same batch;

[0035] The production efficiency of the target production equipment is derived from this T' represents the time required for the target production equipment to produce the same number of workpieces under ideal conditions, T 总 It represents the time taken by the target production equipment to produce the total number of workpieces in the same batch. LM is the production yield of the target production equipment corresponding to the same batch. ω1 and ω2 represent the set weight coefficients respectively.

[0036] In the preferred technical solution of the present application, the number of workpieces assigned to the target production equipment corresponding to each production task is calculated, and the specific calculation process is as follows:

[0037] The currently used production time corresponding to the target production equipment is used as the denominator of the fraction, and the total available production time of the target production equipment is used as the numerator of the fraction, thereby performing fractional operations to calculate the load rate of the target production equipment;

[0038] Comprehensively calculate the weight of each production task corresponding to the target production equipment

[0039] , j is the number of each production task, j = 1, 2, ... J, JH j , WC j , YX j They represent the delivery deadline, estimated completion time and priority of the j-th production task, KY is the available time window of the target production equipment, ω3, ω4, ω5 represent the set influence weight coefficients, and FZ is the load rate of the target production equipment;

[0040] The number of workpieces assigned to the target production equipment for each production task is calculated GM j GM′ j It represents the number of workpieces that need to be produced and the number of workpieces that have been produced for the jth production task.

[0041] A second aspect of the present invention provides a digital intelligent factory production management system based on blockchain, comprising a workpiece quality scoring module (1), an equipment efficiency calculation module (2) and a production task allocation module (3), wherein the workpiece quality scoring module, the equipment efficiency calculation module and the production task allocation module are connected by wired and / or wireless connection to achieve data transmission between the modules;

[0042] Workpiece quality scoring module: a camera is placed at the product drop port of the target production equipment to collect images of each workpiece in the same batch of the target production equipment, thereby determining the quality score of each workpiece in the same batch of the target production equipment;

[0043] Equipment efficiency calculation module: Based on the quality score of each workpiece in the same batch of the target production equipment, the production status evaluation coefficient of the target production equipment is reversely evaluated, and then the production efficiency of the target production equipment is derived;

[0044] Production task allocation module: Calculates the number of workpieces assigned to the target production equipment for each production task based on production efficiency, and feeds back the number of workpieces assigned to the target production equipment for each production task to the equipment control terminal, which then performs corresponding processing on the target production equipment.

[0045] As described above, the present invention provides a blockchain-based digital smart factory production management method, which has at least the following beneficial effects:

[0046] The present invention provides a digital intelligent factory production management method based on blockchain. A camera is arranged at the product drop port of the target production equipment to collect images of each workpiece in the same batch of the target production equipment, so as to determine the quality score of each workpiece in the same batch of the target production equipment; the production status evaluation coefficient of the target production equipment is reversely evaluated, and the production efficiency of the target production equipment is derived; the number of workpieces assigned to the target production equipment corresponding to each production task is calculated based on the production efficiency, and the number of workpieces assigned to the target production equipment corresponding to each production task is fed back to the equipment control terminal, and the equipment control terminal performs corresponding processing on the target production equipment, and through real-time monitoring and analysis of the workpiece quality, potential performance fluctuations or failures of the equipment can be discovered in time to ensure that the equipment operates in the best state; at the same time, the allocation of production tasks is dynamically adjusted based on the production efficiency of the equipment, which can optimize resource utilization, reduce equipment overload or idleness, and improve the flexibility and response speed of the overall production line, thereby achieving more accurate production management, improving product quality and production efficiency, and ultimately enhancing the competitiveness and market adaptability of the factory. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for describing the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0048] Figure 1 It is a schematic diagram of the connection of each step of the method of the present invention.

[0049] Figure 2 It is a schematic diagram of the connection of various modules of the system of the present invention. DETAILED DESCRIPTION

[0050] The above contents in combination with the implementation of the present invention are merely examples and explanations of the concept of the present invention. The technical personnel in the relevant technical field may make various modifications or supplements to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined by the claims, they shall all fall within the protection scope of the present invention.

[0051] Example 1

[0052] See also Figure 1 As shown, a digital intelligent factory production management method based on blockchain includes the following steps:

[0053] A camera is arranged at the product drop port of the target production equipment to collect images of each workpiece in the same batch of the target production equipment, so as to determine the quality score of each workpiece in the same batch of the target production equipment;

[0054] It should be further explained that the camera is deployed at the product drop port of the target production equipment, and the specific deployment parameters include the deployment position and the deployment pitch angle.

[0055] It is necessary to further explain that the specific process of determining the location of the camera at the product drop opening of the target production equipment is as follows:

[0056] Based on the standard size range of the standard workpiece, the maximum width W and the maximum height H of the workpiece are extracted;

[0057] And obtain the type of the corresponding camera to be deployed, based on which the horizontal field of view angle θ of the camera is obtained 水平 and vertical field angle θ 垂直 ;

[0058] This determines the minimum installation distance between the camera and the product drop point

[0059] Obtain the opening direction corresponding to the product drop port, take the product drop point as the center point, make a horizontal extension line to the opening direction corresponding to the product drop port, set the distance of the horizontal extension line to the minimum installation distance, and make a vertical extension line with the end point of the horizontal extension line, obtain the height point where the height of the vertical extension line is consistent with the height of the product drop port as the layout position of the camera at the product drop port of the target production equipment.

[0060] It should be further explained that the pitch angle of the camera at the product drop opening of the target production equipment is determined in the following specific process:

[0061] By calculating the formula Calculate the pitch angle θ′ of the camera at the product drop opening of the target production equipment, H 布设 The height of the product drop opening.

[0062] Based on the quality score of each workpiece in the same batch of the target production equipment, the production status evaluation coefficient of the target production equipment is reversely evaluated, and then the production efficiency of the target production equipment is derived;

[0063] It should be further explained that the process of determining the quality score of each workpiece in the same batch of the target production equipment is as follows:

[0064] The convolutional neural network model is used to detect the images of each workpiece corresponding to the target production equipment to obtain the defect features of each workpiece corresponding to the target production equipment; the size features of each workpiece corresponding to the target production equipment are measured by image processing technology; the color features of each workpiece corresponding to the target production equipment are analyzed by color space conversion; the above defect features, size features and color features are combined into a feature vector I corresponding to each workpiece of the target production equipment i , i is the number of each workpiece, i = 1, 2, ... N, N is the total number of workpieces in the same batch;

[0065] Obtain the standard feature vector I′ of the workpiece corresponding to the target production equipment. For each workpiece i, calculate the similarity between its feature vector and the standard feature vector. || || is the norm symbol;

[0066] Where S(I) i The result is between [-1,1], and the closer it is to 1, the more the workpiece meets the standard;

[0067] Based on the similarity between the feature vector of each workpiece corresponding to the target production equipment and the standard feature vector, the quality score of each workpiece corresponding to the target production equipment is obtained. α is the threshold value of similarity, which indicates the minimum similarity requirement between the workpiece and the standard feature vector. When the similarity is higher than the threshold, the workpiece is considered qualified; when the similarity is lower than the threshold, the quality score will be reduced proportionally.

[0068] It should be further explained that the production status evaluation coefficient of the target production equipment is evaluated, and the specific evaluation process is as follows:

[0069] Average quality score of products in the same batch based on the target production equipment And the standard deviation of the quality scores of the target production equipment corresponding to the workpieces in the same batch Comprehensively define the volatility coefficient ε of the target production equipment corresponding to the same batch of workpieces;

[0070] Then use the calculation formula Evaluate the production status evaluation coefficient ZT of the target production equipment, where α3 is a predefined weight factor used to adjust the relative importance of the average quality score and volatility of the equipment. The larger α3 is, the more attention is paid to the average quality score of the batch, and the smaller α3 is, the more attention is paid to the volatility of the workpiece quality. Q' represents the benchmark quality score of the production equipment under ideal conditions.

[0071] It indicates the ratio of the average quality score of a batch of workpieces to the benchmark score under ideal conditions. The closer the ratio is to 1, the closer the equipment condition is to the ideal condition.

[0072] ε is a function of the quality score volatility, which reflects the stability of equipment production. The smaller the volatility, the more stable the equipment state, and vice versa, the greater the volatility, the more unstable the equipment state.

[0073] It should be further explained that the volatility coefficient ε of the target production equipment corresponding to the same batch of workpieces is comprehensively defined. The specific definition process is:

[0074] The inclination is introduced to reflect the distribution of the workpiece quality score. The calculation formula for the inclination of the quality score of the same batch of workpieces of the specific target production equipment is as follows:

[0075] QX is the quality score inclination of the target production equipment corresponding to the same batch of workpieces;

[0076] Skewness reflects the asymmetry of data distribution and can capture extreme cases in quality scores. For example, if most workpieces have high quality scores, but a few have extremely low scores, the skewness will be large, reflecting that there may be occasional equipment failures in the production process. By introducing skewness, the status of the equipment can be more comprehensively evaluated;

[0077] The design target production equipment corresponds to the initial volatility coefficient of the same batch of workpieces. The specific formula is shown as follows:

[0078]

[0079] Where e is a natural constant, α1 is the preset sensitivity threshold of control volatility to device status, σ0 is the predefined volatility threshold, and when σ Q =σ0, ε1=0.5, indicating that the target production equipment is in a critical state. Q <σ0, ε1 approaches 1, indicating that the target production equipment has a small volatility and the equipment state is stable. Q >σ0, ε1 approaches 0, indicating that the target production equipment has large volatility and the equipment status is unstable;

[0080] The first generation of volatility coefficients used an exponential decay form to indicate that the larger the standard deviation, the faster the volatility coefficient value decays, reflecting the instability of the production process, that is, when the volatility exceeds a certain threshold, the equipment status will deteriorate rapidly. The value of the exponential decay function is in σ Q = 0 is 1, indicating no fluctuation and the equipment status is very stable; Q As it increases, the function value gradually decreases, reflecting the negative impact of volatility on the equipment status;

[0081] The initial volatility coefficient of the target production equipment corresponding to the same batch of workpieces is combined with the quality score inclination of the target production equipment corresponding to the same batch of workpieces, and the volatility coefficient ε=ε1×(1-α2×|QX|) of the target production equipment corresponding to the same batch of workpieces is obtained comprehensively, where α2 is the preset influence value of the control inclination on the volatility coefficient. The larger the inclination, the smaller the volatility coefficient value.

[0082] The penalty term 1-α2×|QX| for skewness in the volatility coefficient is reasonable. The larger the skewness, the more obvious the penalty term, which reflects that the equipment may be unstable or abnormal during the production process.

[0083] It should be further explained that the production efficiency of the target production equipment is derived, and the specific derivation process includes the following steps:

[0084] Based on the quality score of each workpiece in the same batch corresponding to the target production equipment, it is compared with a predefined quality score threshold, each workpiece with a quality score greater than the predefined quality score threshold is counted as a qualified workpiece, the total number of qualified workpieces is counted, and the ratio operation is performed on it with the total number of workpieces in the same batch to obtain the production yield of the target production equipment in the same batch;

[0085] The production efficiency of the target production equipment is derived from this T' represents the time required for the target production equipment to produce the same number of workpieces under ideal conditions, T 总 It represents the time taken by the target production equipment to produce the total number of workpieces in the same batch. LM is the production yield of the target production equipment corresponding to the same batch. ω1 and ω2 represent the set weight coefficients respectively.

[0086] The better the ZT equipment status (ZT is close to 1), the higher the production efficiency. If the equipment status is poor (ZT is close to 0), the production efficiency will drop significantly even if other conditions are good.

[0087] The higher the average quality score of the workpiece, the better the quality control of the equipment during the production process, and the production efficiency will be improved accordingly.

[0088] σ Q The greater the quality fluctuation, the lower the production efficiency.

[0089] The fifth calculation parameter indicates that the closer the actual production time is to the ideal time, the higher the production efficiency. If the equipment runs slowly, the production efficiency will decrease.

[0090] The higher the production yield, the higher the production efficiency. If there are more waste products during the production process, the production efficiency will be reduced accordingly.

[0091] The number of workpieces assigned to the target production equipment for each production task is calculated based on production efficiency, and the number of workpieces assigned to the target production equipment for each production task is fed back to the equipment control terminal, which then performs corresponding processing on the target production equipment.

[0092] It should be further explained that the number of workpieces assigned to the target production equipment corresponding to each production task is calculated. The specific calculation process is as follows:

[0093] The currently used production time corresponding to the target production equipment is used as the denominator of the fraction, and the total available production time of the target production equipment is used as the numerator of the fraction, thereby performing fractional operations to calculate the load rate of the target production equipment;

[0094] Comprehensively calculate the weight of each production task corresponding to the target production equipment

[0095] , j is the number of each production task, j = 1, 2, ... J, JH j , WC j , YX j They represent the delivery deadline, estimated completion time and priority of the j-th production task, KY is the available time window of the target production equipment, ω3, ω4, ω5 represent the set influence weight coefficients, and FZ is the load rate of the target production equipment;

[0096] The second calculation parameter represents the production efficiency of the target production equipment. The higher the efficiency, the more suitable the production equipment is for the task. The greater the production efficiency, the greater the weight of the target production equipment corresponding to each production task.

[0097] The third calculation parameter represents the load impact factor of the equipment. The higher the load, the less suitable the equipment is for taking on new tasks. ω4 represents the degree of influence of the control load on task allocation;

[0098] The fourth calculation parameter represents the task priority and delivery date influencing factor. The higher the priority, the more urgent the task, the greater the weight of the target production equipment corresponding to each production task. The smaller the difference between the delivery deadline and the expected completion time, the more urgent the task, and the greater the weight of the target production equipment corresponding to each production task. ω5 is the impact of the delivery deadline on task allocation.

[0099] The fifth calculation parameter indicates the degree of match between the available time window of the equipment and the task time. If the available time KY of the equipment is sufficient to complete the task KY ≥ WC j , then this item is 1; if the available time of the device is insufficient to complete the task, then this item is It means that the equipment can only partially undertake the task;

[0100] The number of workpieces assigned to the target production equipment for each production task is calculated GM j GM′ j It represents the number of workpieces that need to be produced and the number of workpieces that have been produced for the jth production task.

[0101] Example 2

[0102] See also Figure 2 As shown, a digital intelligent factory production management system based on blockchain includes a workpiece quality scoring module (1), an equipment efficiency calculation module (2) and a production task allocation module (3), wherein the workpiece quality scoring module, the equipment efficiency calculation module and the production task allocation module are connected by wired and / or wireless connection to realize data transmission between the modules;

[0103] Workpiece quality scoring module: a camera is placed at the product drop port of the target production equipment to collect images of each workpiece in the same batch of the target production equipment, thereby determining the quality score of each workpiece in the same batch of the target production equipment;

[0104] Equipment efficiency calculation module: Based on the quality score of each workpiece in the same batch of the target production equipment, the production status evaluation coefficient of the target production equipment is reversely evaluated, and then the production efficiency of the target production equipment is derived;

[0105] Production task allocation module: Calculates the number of workpieces assigned to the target production equipment for each production task based on production efficiency, and feeds back the number of workpieces assigned to the target production equipment for each production task to the equipment control terminal, which then performs corresponding processing on the target production equipment.

[0106] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0107] It should be understood that determining B based on A does not mean determining B only based on A. B can also be determined based on A and / or other information.

[0108] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0109] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A digital intelligent factory production management method based on blockchain, characterized in that: include: A camera is arranged at the product drop port of the target production equipment to collect images of each workpiece in the same batch of the target production equipment, so as to determine the quality score of each workpiece in the same batch of the target production equipment; Based on the quality score of each workpiece in the same batch of the target production equipment, the production status evaluation coefficient of the target production equipment is reversely evaluated, and then the production efficiency of the target production equipment is derived; Calculate the number of workpieces assigned to the target production equipment for each production task based on production efficiency, and feed back the number of workpieces assigned to the target production equipment for each production task to the equipment control terminal, which then processes the target production equipment accordingly; Evaluate the production status evaluation coefficient of the target production equipment. The specific evaluation process is as follows: Average quality score of products in the same batch based on the target production equipment And the standard deviation of the quality scores of the target production equipment corresponding to the workpieces in the same batch Comprehensively define the volatility coefficient ε of the target production equipment corresponding to the same batch of workpieces, where Q i is the quality score of each workpiece corresponding to the target production equipment, and N is the total number of workpieces in the same batch; Then use the calculation formula Evaluate the production status evaluation coefficient ZT of the target production equipment, where α3 is a predefined weight factor used to adjust the relative importance of the average quality score and volatility of the equipment, and Q' represents the benchmark quality score of the production equipment under ideal conditions; The volatility coefficient ε of the target production equipment corresponding to the same batch of workpieces is comprehensively defined. The specific definition process is: The inclination is introduced to reflect the distribution of the workpiece quality score. The calculation formula for the inclination of the quality score of the same batch of workpieces of the specific target production equipment is as follows: QX is the quality score inclination of the target production equipment corresponding to the same batch of workpieces; The design target production equipment corresponds to the initial volatility coefficient of the same batch of workpieces. The specific formula is shown as follows: Where e is a natural constant, α1 is the preset sensitivity threshold of control volatility to device status, σ0 is the predefined volatility threshold, and when σ Q =σ0, ε1=0.5, indicating that the target production equipment is in a critical state. Q <σ0, ε1 approaches 1, indicating that the target production equipment has a small volatility and the equipment state is stable. Q >σ0, ε1 approaches 0, indicating that the target production equipment has large volatility and the equipment status is unstable; The initial volatility coefficient of the target production equipment corresponding to the same batch of workpieces is combined with the quality score inclination of the target production equipment corresponding to the same batch of workpieces, and the volatility coefficient ε=ε1×(1-α2×|QX|) of the target production equipment corresponding to the same batch of workpieces is obtained comprehensively, where α2 is the preset influence value of the control inclination on the volatility coefficient. The larger the inclination, the smaller the volatility coefficient value.

2. According to a blockchain-based digital smart factory production management method according to claim 1, it is characterized in that: A camera is placed at the product drop port of the target production equipment. Specific placement parameters include placement position and placement pitch angle.

3. According to a blockchain-based digital intelligent factory production management method according to claim 2, it is characterized in that: Determine the camera's placement position at the product drop-off point of the target production equipment. The specific determination process is as follows: Based on the standard size range of the standard workpiece, the maximum width W and the maximum height H of the workpiece are extracted; And obtain the type of the corresponding camera to be deployed, based on which the horizontal field of view angle θ of the camera is obtained 水平 and vertical field angle θ 垂直 ; This determines the minimum installation distance between the camera and the product drop point Obtain the opening direction corresponding to the product drop port, take the product drop point as the center point, make a horizontal extension line to the opening direction corresponding to the product drop port, set the distance of the horizontal extension line to the minimum installation distance, and make a vertical extension line with the end point of the horizontal extension line, obtain the height point where the height of the vertical extension line is consistent with the height of the product drop port as the layout position of the camera at the product drop port of the target production equipment.

4. According to a blockchain-based digital intelligent factory production management method according to claim 2, it is characterized in that: Determine the pitch angle of the camera at the product drop opening of the target production equipment. The specific determination process is as follows: By calculating the formula Calculate the pitch angle θ′ of the camera at the product drop opening of the target production equipment, H 布设 The height of the product drop opening.

5. According to a blockchain-based digital intelligent factory production management method according to claim 1, it is characterized in that: The process of determining the quality score of each workpiece in the same batch for the target production equipment is as follows: The convolutional neural network model is used to detect the images of each workpiece corresponding to the target production equipment to obtain the defect features of each workpiece corresponding to the target production equipment; the size features of each workpiece corresponding to the target production equipment are measured by image processing technology; the color features of each workpiece corresponding to the target production equipment are analyzed by color space conversion; the above defect features, size features and color features are combined into a feature vector I corresponding to each workpiece of the target production equipment i , i is the number of each workpiece, i = 1, 2, ... N, N is the total number of workpieces in the same batch; Obtain the standard feature vector I′ of the workpiece corresponding to the target production equipment. For each workpiece i, calculate the similarity between its feature vector and the standard feature vector. || || is the norm symbol; Based on the similarity between the feature vector of each workpiece corresponding to the target production equipment and the standard feature vector, the quality score of each workpiece corresponding to the target production equipment is obtained. α is the similarity threshold.

6. According to a blockchain-based digital intelligent factory production management method according to claim 1, it is characterized in that: The production efficiency of the target production equipment is derived. The specific derivation process includes the following steps: Based on the quality score of each workpiece in the same batch corresponding to the target production equipment, it is compared with a predefined quality score threshold, each workpiece with a quality score greater than the predefined quality score threshold is counted as a qualified workpiece, the total number of qualified workpieces is counted, and the ratio operation is performed on it with the total number of workpieces in the same batch to obtain the production yield of the target production equipment in the same batch; The production efficiency of the target production equipment is derived from this T' represents the time required for the target production equipment to produce the same number of workpieces under ideal conditions, T 总 It represents the time taken by the target production equipment to produce the total number of workpieces in the same batch. LM is the production yield of the target production equipment corresponding to the same batch. ω1 and ω2 represent the set weight coefficients respectively.

7. According to a blockchain-based digital intelligent factory production management method according to claim 6, it is characterized in that: The number of workpieces assigned to the target production equipment for each production task is calculated. The specific calculation process is as follows: The currently used production time corresponding to the target production equipment is used as the denominator of the fraction, and the total available production time of the target production equipment is used as the numerator of the fraction, thereby performing fractional operations to calculate the load rate of the target production equipment; Comprehensively calculate the weight of each production task corresponding to the target production equipment j is the number of each production task, j = 1, 2, ... J, JH j , WC j , YX j They represent the delivery deadline, estimated completion time and priority of the j-th production task, KY is the available time window of the target production equipment, ω3, ω4, ω5 represent the set influence weight coefficients, and FZ is the load rate of the target production equipment; The number of workpieces assigned to the target production equipment for each production task is calculated GM j GM′ j It represents the number of workpieces that need to be produced and the number of workpieces that have been produced for the jth production task.

8. A digital smart factory production management system based on blockchain, characterized in that: It is implemented based on a blockchain-based digital smart factory production management method according to any one of claims 1 to 7, comprising a workpiece quality scoring module (1), an equipment efficiency calculation module (2) and a production task allocation module (3), wherein the workpiece quality scoring module, the equipment efficiency calculation module and the production task allocation module are connected by wired and / or wireless connection to realize data transmission between the modules; Workpiece quality scoring module: a camera is placed at the product drop port of the target production equipment to collect images of each workpiece in the same batch of the target production equipment, thereby determining the quality score of each workpiece in the same batch of the target production equipment; Equipment efficiency calculation module: Based on the quality score of each workpiece in the same batch of the target production equipment, the production status evaluation coefficient of the target production equipment is reversely evaluated, and then the production efficiency of the target production equipment is derived; Production task allocation module: Calculates the number of workpieces assigned to the target production equipment for each production task based on production efficiency, and feeds back the number of workpieces assigned to the target production equipment for each production task to the equipment control terminal, which then performs corresponding processing on the target production equipment.

Images