1. An intelligent production model of industrial machinery based on a block chain comprises the following specific steps:

step 1, acquiring an equipment real-time information table by using various sensors and system software and uploading the information table to a block chain node, wherein the method comprises the following steps: equipment type, mechanical parameters, monitoring parameters and task state;

step 2, integrating and storing the uploaded real-time information table of the equipment by using a block chain technology;

step 3, acquiring data from the block chain, processing the data by using a model algorithm, wherein the big data is subjected to feature mining by using K nearest neighbor KNN, health assessment and planning of equipment are completed by using an Alexnet migration learning model, and scheduling of mechanical equipment is optimized by using an adaptive genetic algorithm AGA;

and 4, obtaining a corresponding analysis result, wherein the analysis result comprises the following steps: equipment health assessment, optimal scheduling scheme, reasonable planning of working path and guidance of production and manufacturing.

2. The intelligent production model of block chain based industrial machinery according to claim 1, wherein: the parameters contained in the real-time information table of the device in the step 1 are as follows:

the equipment types comprise an excavator, a pump truck, a crane, an engineering truck and the like; the mechanical parameters comprise mechanical model, service life, factory parameters, rated load and the like; the monitoring parameters comprise pre-tightening force corresponding to the strain gauge, vibration signals corresponding to the rotary component, the lubricating oil parameters comprise oil temperature and the proportion of components contained in the oil, and the working environment comprises temperature, humidity and wind power level.

3. The intelligent production model of block chain based industrial machinery according to claim 1, wherein: and 2, uploading the integrated information table to a block chain node, wherein the block chain node is characterized in that:

when the uploaded data is developed towards the public, the current node can be accessed into the public chain; instead, when data is returned to the company or country, the building of the private chain may be selected.

4. The intelligent production model of block chain based industrial machinery according to claim 1, wherein: the concrete steps of model data processing and analysis in the step 3 are as follows:

step 3.1, performing feature mining on the big data by using a KNN algorithm, wherein the method specifically comprises the following steps:

step 3.1.1, predetermining the number K of clustering centers, and initializing the positions of the K clustering centers;

step 3.1.2, calculating all data to the nearest clustering center and calculating the corresponding Euclidean distance;

step 3.1.3, updating the clustering center of the clustering cluster determined in the step 3.1.2, and solving an arithmetic mean for each dimension according to an updating rule;

step 3.1.4, repeating the steps 3.1.1 to 3.1.3 until the iteration times or the set convergence error is reached;

step 3.2, health evaluation and working path planning of the equipment are completed by utilizing an Alexnet migration learning model; the method comprises the following specific steps:

step 3.2.1, building an Alexnet model by utilizing a TensorFlow framework, and training the model by using prior data so as to converge the model;

step 3.2.2, changing the specification size of the output layer of the trained model, initializing the weight coefficient of the output layer into a random value, and keeping the weights of other layers;

step 3.2.3, training a migration model on a target training set which needs to be migrated so as to make the model converged;

3.3, optimizing the dispatching of the mechanical equipment by using a self-adaptive genetic algorithm, wherein the method comprises the following specific steps of:

step 3.3.1, initializing genetic algorithm parameters, wherein the initialization comprises the following steps: initial population size, variation probability, cross probability and maximum iteration number;

3.3.2, generating a layout scheme of the first generation population by using a random number to complete initialization;

step 3.3.3, calculating the fitness corresponding to all individuals in the population of the current generation, and simultaneously solving the individual fitness value and the average fitness value of the optimal population;

step 3.3.4, performing adaptive genetic processing, which comprises: selecting, crossing and mutating, and turning to the step 3.3.3 after the population state is updated;

and 3.3.5, obtaining an optimal solving result after the iteration termination condition is reached.

5. The intelligent production model of block chain based industrial machinery according to claim 1, wherein: and 4, obtaining a corresponding analysis result, which is characterized by comprising the following steps:

obtaining the current health result of the equipment, and carrying out related maintenance according to the result, such as lubricating oil replacement and damaged part maintenance; obtaining an optimal scheduling scheme, and calling mechanical equipment in each place according to the given scheme to complete corresponding tasks at the lowest cost in the shortest time; the working path is reasonably planned, the production and manufacturing are guided, the whole service life model of the mechanical equipment can well guide and optimize the processes of relevant manufacturers in the production process and the like.

Background

As a developing big country, the achievement obtained by the capital construction of China in recent years is the goal of drawing attention, and the Chinese is once named as 'capital construction magic' and meets the capital construction level of China. At present, advanced technologies such as cloud computing technology, 5G communication, deep learning and the like are rapidly developed, and China completely has technical conditions and corresponding strength to accelerate the intelligentized pace of mechanical production. In 2019, 11 and 7 months, the xu worker and China Unicom signed a 5G smart factory and a strategic cooperation agreement of the Internet of things, so that the technical research cooperation of deep fusion in the industrial field is developed, a business enabling platform based on the Internet of things is jointly built, and an intelligent and advanced 5G smart factory is fused and created. For the engineering machinery, the variety is many and varied, the distribution is wide, the centralized management is difficult, meanwhile, in the face of the huge number of mechanical engineering equipment, certain difficulty exists in the aspect of scheduling, and how to reasonably and efficiently plan the optimal scheduling scheme is really a challenge.

The blockchain technology is widely applied in recent years as a decentralized shared database, with its excellent decentralized thought and performance expected to be high, and the blockchain technology is used to store many and miscellaneous engineering machine data, so that on one hand, the data is efficiently utilized, and on the other hand, the shared big data can improve the generalization of the algorithm model. In the aspect of algorithms, in the face of massive data, some data mining algorithms such as K Nearest Neighbor (KNN) show strong performance, deep learning models such as Alexnet and CNN can well extract features, and how to optimize and improve the algorithms on the basis of the existing scheduling algorithms for the problem of challenging engineering machinery scheduling, the algorithm is worthy of being considered, and the adaptive genetic algorithm has a strong function in the aspect.

The domestic patents related to block chains and intellectualization comprise an unmanned aerial vehicle intelligent farmland information acquisition and monitoring system and method based on the block chains (201911370408.7), information acquired by an unmanned aerial vehicle is transmitted to block chain nodes, then the variety, yield estimation, growth state, water and fertilizer information and plant disease and pest information of crops are obtained based on the node information of the block chains, and the information of the farmland is returned by means of a deep learning model, but the deep learning model is not elaborated in more detail in the patent. The national invention patent 'a block chain consensus method and system based on deep learning model training' (202010318933.0), which introduces excessive computational power of a block chain into the deep learning model training, and enables investors to use an ore machine for artificial intelligence model training through an incentive mechanism of the block chain, so as to solve the problem of insufficient computational power and high cost.

Disclosure of Invention

In order to solve the problems, the invention provides an intelligent production model of industrial machinery based on a block chain on the basis of a block chain technology, a KNN (K nearest neighbor) and Alexnet migration learning model and an Adaptive Genetic Algorithm (AGA). In the model, the state parameters of mechanical equipment are considered from multiple dimensions and multiple angles, so that a corresponding description model can be constructed more comprehensively, and meanwhile, the block chain technology is adopted, and uploaded data can be stored, shared and used more quickly and efficiently. In an algorithm module of the model, a KNN, Alexnet migration learning model and an AGA algorithm are adopted, so that information contained in big data can be better mined, and therefore accurate and effective health maintenance strategies, optimal scheduling algorithms, guidance of intelligent equipment processing technological processes and the like are improved. To achieve the purpose, the invention provides an intelligent production model of an industrial machine based on a block chain, which comprises the following specific steps:

step 1, acquiring an equipment real-time information table by using various sensors and system software and uploading the information table to a block chain node, wherein the method comprises the following steps: equipment type, mechanical parameters, monitoring parameters and task state;

further, the parameters contained in the real-time information table of the device in step 1 include:

the equipment types comprise an excavator, a pump truck, a crane, an engineering truck and the like; the mechanical parameters comprise mechanical model, service life, factory parameters, rated load and the like; the monitoring parameters comprise pre-tightening force corresponding to the strain gauge, vibration signals corresponding to the rotary component, lubricating oil parameters (oil temperature and the proportion of components contained in the oil) and working environment (temperature, humidity, wind power level and the like).

Step 2, integrating and storing the uploaded real-time information table of the equipment by using a block chain technology;

further, the integrated information table is uploaded to a block chain node in step 2, and the method is characterized in that:

when the uploaded data is developed towards the public, the current node can be accessed into the public chain; instead, when data is returned to the company or country, the building of the private chain may be selected.

Step 3, acquiring data from the block chain, processing the data by using a model algorithm, wherein the big data is subjected to feature mining by using K Nearest Neighbor (KNN), health assessment and planning of equipment are completed by using an Alexnet migration learning model, and scheduling of mechanical equipment is optimized by using a self-adaptive genetic algorithm;

further, the specific steps of processing and analyzing the model data in step 3 are as follows:

step 3.1, performing feature mining on the big data by using a KNN algorithm, wherein the method specifically comprises the following steps:

step 3.1.1, predetermining the number K of clustering centers, and initializing the positions of the K clustering centers;

step 3.1.2, calculating all data to the nearest clustering center and calculating the corresponding Euclidean distance;

step 3.1.3, updating the clustering center of the clustering cluster determined in the step 3.1.2, and solving an arithmetic mean for each dimension according to an updating rule;

and 3.1.4, repeating the steps 3.1.1 to 3.1.3 until the iteration times or the set convergence error is reached.

Step 3.2, health evaluation and working path planning of the equipment are completed by utilizing an Alexnet migration learning model; the method comprises the following specific steps:

step 3.2.1, building an Alexnet model by utilizing a TensorFlow framework, and training the model by using prior data so as to converge the model;

step 3.2.2, changing the specification size of the output layer of the trained model, initializing the weight coefficient of the output layer into a random value, and keeping the weights of other layers;

and 3.2.3, training a migration model on a target training set which wants to migrate, so that the model converges.

3.3, optimizing the dispatching of the mechanical equipment by using a self-adaptive genetic algorithm, wherein the method comprises the following specific steps of:

step 3.3.1, initializing genetic algorithm parameters, wherein the initialization comprises the following steps: initial population size, variation probability, cross probability and maximum iteration number;

3.3.2, generating a layout scheme of the first generation population by using a random number to complete initialization;

step 3.3.3, calculating the fitness corresponding to all individuals in the population of the current generation, and simultaneously solving the individual fitness value and the average fitness value of the optimal population;

step 3.3.4, performing adaptive genetic processing, which comprises: selection, crossover, mutation. After the population state updating is finished, turning to the step 3.3.3;

and 3.3.5, obtaining an optimal solving result after the iteration termination condition is reached.

And 4, obtaining a corresponding analysis result, wherein the analysis result comprises the following steps: equipment health assessment, optimal scheduling scheme, reasonable planning of working path and guidance of production and manufacturing.

Further, step 4 obtains the corresponding analysis result, which is characterized in that:

obtaining the current health result of the equipment, and carrying out related maintenance according to the result, such as lubricating oil replacement and damaged part maintenance; obtaining an optimal scheduling scheme, and calling mechanical equipment in each place according to the given scheme to complete corresponding tasks at the lowest cost in the shortest time; the working path is reasonably planned, the production and manufacturing are guided, the whole service life model of the mechanical equipment can well guide and optimize the processes of relevant manufacturers in the production process and the like.

The invention relates to an intelligent production model of industrial machinery based on a block chain, which has the advantages that: the invention has the technical effects that:

1. according to the invention, the state parameters of mechanical equipment are considered from multiple dimensions and angles, so that a corresponding description model can be more comprehensively constructed;

2. the block chain technology is adopted, so that the uploaded data can be stored, shared and used more quickly and efficiently, and the algorithm model can be helped to improve the generalization capability of the algorithm model;

3. the invention adopts KNN, Alexnet transfer learning model and AGA algorithm, which can better mine the information contained in the big data, thereby improving the accurate and effective health maintenance strategy, the optimal scheduling algorithm, the intelligent processing process flow of the guidance equipment and the like.

Drawings

FIG. 1 is a diagram of a model architecture of the present invention;

Detailed Description

The invention is described in further detail below with reference to the following detailed description and accompanying drawings:

the invention provides an intelligent production model of an industrial machine based on a block chain, aiming at realizing production guidance of the industrial machine, reducing the operation cost and improving the production efficiency.

FIG. 1 is a diagram of a model architecture of the present invention. The steps of the present invention will be described in detail below with reference to the structural diagrams.

Step 1, acquiring an equipment real-time information table by using various sensors and system software and uploading the information table to a block chain node, wherein the method comprises the following steps: equipment type, mechanical parameters, monitoring parameters and task state;

further, the parameters contained in the real-time information table of the device in step 1 include:

the equipment types comprise an excavator, a pump truck, a crane, an engineering truck and the like; the mechanical parameters comprise mechanical model, service life, factory parameters, rated load and the like; the monitoring parameters comprise pre-tightening force corresponding to the strain gauge, vibration signals corresponding to the rotary component, lubricating oil parameters (oil temperature and the proportion of components contained in the oil) and working environment (temperature, humidity, wind power level and the like).

Step 2, integrating and storing the uploaded real-time information table of the equipment by using a block chain technology;

further, the integrated information table is uploaded to a block chain node in step 2, and the method is characterized in that:

when the uploaded data is developed towards the public, the current node can be accessed into the public chain; instead, when data is returned to the company or country, the building of the private chain may be selected.

Step 3, acquiring data from the block chain, processing the data by using a model algorithm, wherein the big data is subjected to feature mining by using K Nearest Neighbor (KNN), health assessment and planning of equipment are completed by using an Alexnet migration learning model, and scheduling of mechanical equipment is optimized by using a self-adaptive genetic algorithm;

further, the specific steps of processing and analyzing the model data in step 3 are as follows:

step 3.1, performing feature mining on the big data by using a KNN algorithm, wherein the method specifically comprises the following steps:

step 3.1.1, predetermining the number K of clustering centers, and initializing the positions of the K clustering centers;

step 3.1.2, calculating all data to the nearest clustering center and calculating the corresponding Euclidean distance;

step 3.1.3, updating the clustering center of the clustering cluster determined in the step 3.1.2, and solving an arithmetic mean for each dimension according to an updating rule;

and 3.1.4, repeating the steps 3.1.1 to 3.1.3 until the iteration times or the set convergence error is reached.

Step 3.2, health evaluation and working path planning of the equipment are completed by utilizing an Alexnet migration learning model; the method comprises the following specific steps:

step 3.2.1, building an Alexnet model by utilizing a TensorFlow framework, and training the model by using prior data so as to converge the model;

step 3.2.2, changing the specification size of the output layer of the trained model, initializing the weight coefficient of the output layer into a random value, and keeping the weights of other layers;

and 3.2.3, training a migration model on a target training set which wants to migrate, so that the model converges.

3.3, optimizing the dispatching of the mechanical equipment by using a self-adaptive genetic algorithm, wherein the method comprises the following specific steps of:

step 3.3.1, initializing genetic algorithm parameters, wherein the initialization comprises the following steps: initial population size, variation probability, cross probability and maximum iteration number;

3.3.2, generating a layout scheme of the first generation population by using a random number to complete initialization;

step 3.3.3, calculating the fitness corresponding to all individuals in the population of the current generation, and simultaneously solving the individual fitness value and the average fitness value of the optimal population;

step 3.3.4, performing adaptive genetic processing, which comprises: selection, crossover, mutation. After the population state updating is finished, turning to the step 3.3.3;

and 3.3.5, obtaining an optimal solving result after the iteration termination condition is reached.

And 4, obtaining a corresponding analysis result, wherein the analysis result comprises the following steps: equipment health assessment, optimal scheduling scheme, reasonable planning of working path and guidance of production and manufacturing.

Further, step 4 obtains the corresponding analysis result, which is characterized in that:

obtaining the current health result of the equipment, and carrying out related maintenance according to the result, such as lubricating oil replacement and damaged part maintenance; obtaining an optimal scheduling scheme, and calling mechanical equipment in each place according to the given scheme to complete corresponding tasks at the lowest cost in the shortest time; the working path is reasonably planned, the production and manufacturing are guided, the whole service life model of the mechanical equipment can well guide and optimize the processes of relevant manufacturers in the production process and the like.

The above description is only a preferred embodiment of the present invention, and is not intended to limit the present invention in any way, but any modifications or equivalent variations made according to the technical spirit of the present invention are within the scope of the present invention as claimed.