Automatic wiring system of efficient assembly type machine room

Abstract

The invention relates to the technical field of artificial intelligence, in particular to an automatic wiring system of an efficient assembly type machine room, which comprises a wiring planning subsystem, an automatic execution subsystem, an intelligent management subsystem and a data analysis subsystem, and is characterized in that the automatic execution subsystem comprises an automatic wiring robot and an environment sensing module; the wiring planning subsystem comprises a data collection module, a path planning module and a path planning module, according to the scheme, an HGE-ARCO model is adopted in the path planning module to generate a preliminary wiring path, the wiring path is rapidly adjusted according to real-time data, and the wiring path is flexibly adjusted according to machine room layout and equipment changes; the genetic algorithm is combined with the ant colony algorithm in the HGE-ARCO model, the pheromone concentration is dynamically adjusted according to the expression of the path in the wiring process, subsequent path selection is guided, and a better wiring path is found.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to an automated wiring system for a highly efficient assembled computer room. Background Art

[0002] With the rapid development of information technology and the rapid growth of data centers, the wiring requirements of computer rooms are becoming increasingly complex. Traditional manual wiring methods have problems such as low efficiency, high error rate and high adaptability. Manual intervention leads to a slow wiring process, resulting in a waste of time, and is prone to connection errors and path overlap. In addition, when the equipment and layout of the computer room change, it is difficult for traditional systems to quickly adjust and optimize the wiring. Summary of the invention

[0003] In view of the above situation, in order to overcome the defects of the prior art, the present invention provides an efficient automated wiring system for prefabricated computer rooms. In view of the problems of low efficiency, high error rate and high adaptability of traditional manual wiring methods, the present invention adopts the HGE-ARCO model (Hybrid Genetic Evolution-based Adaptive ResourceCooperation model) in the path planning module to generate a preliminary wiring path, quickly adjust the wiring path according to real-time data, and use the model to generate the wiring path to reduce the incidence of human errors. The wiring path can be flexibly adjusted according to the layout of the computer room and equipment changes; the present invention uses the population mechanism of the genetic algorithm in the HGE-ARCO model to find a better wiring path, and at the same time adopts the pheromone concept of the ant colony algorithm, which can dynamically adjust the pheromone concentration according to the performance of the path during the wiring process to guide subsequent path selection.

[0004] The technical solution adopted by the present invention is as follows: The automated wiring system for an efficient prefabricated computer room provided by the present invention includes a wiring planning subsystem, an automated execution subsystem, an intelligent management subsystem and a data analysis subsystem, specifically including the following contents:

[0005] The wiring planning subsystem includes a data collection module, a path planning module and an optimization strategy module;

[0006] The automated execution subsystem includes an automatic wiring robot and an environment perception module;

[0007] The intelligent management subsystem includes a real-time monitoring module, a fault detection module and an adaptive scheduling module;

[0008] The data analysis subsystem includes a storage module, a data analysis module and a visualization interface.

[0009] Furthermore, the wiring planning subsystem specifically includes the following contents:

[0010] The data collection module collects cabling data, including room layout, equipment location, connection requirements, cable types and length requirements;

[0011] The path planning module generates a preliminary routing path based on the routing data using the HGE-ARCO model;

[0012] The optimization strategy module optimizes the wiring path, obtains the optimal wiring path and converts it into operation instructions.

[0013] Furthermore, the automated execution subsystem specifically includes the following contents:

[0014] The automatic wiring robot is equipped with a robotic arm, sensors, cameras and a control unit, which lays cables according to the optimal wiring path and operating instructions;

[0015] The environmental perception module collects real-time environmental information through sensors in the automatic wiring robot, including obstacles and position changes of other equipment, and adjusts the optimal wiring path.

[0016] Furthermore, the intelligent management subsystem specifically includes the following contents:

[0017] The real-time monitoring module monitors the wiring process in real time through sensors and cameras installed on the robot, and uses cameras to detect the wiring status;

[0018] The fault detection module detects whether there is a short circuit, open circuit or poor contact through connectivity testing, and locates the problem area through intelligent analysis algorithms;

[0019] The adaptive scheduling module adjusts the wiring plan according to the adjusted optimal wiring path obtained by the environment perception module.

[0020] Furthermore, in the path planning module, the HGE-ARCO model is used to generate a preliminary routing path, which specifically includes the following steps:

[0021] Step S1: Initialization, initialize N search agent groups S according to the wiring data I ,The search agent group is composed of individual search agents, and the position of each individual search agent represents a routing path;

[0022] Step S2: Define constraints, including physical limitations of the wiring path, cable length limitations, and connection point requirements, including the following:

[0023] Physical limitations: S I =llb I +rand*(uub I -llb I );

[0024] Among them, S I To search for proxy groups, llb I and uub I are the lower and upper bounds of the search space, and rand is the random number generator;

[0025] Randomly assign volume V o and density D n ;

[0026] Acceleration A I A is randomly generated from the upper and lower limits of acceleration. I The process is as follows:

[0027] A I =aab I +rand*(kkb I -aab I );

[0028] Among them, V o is the number of connection points and cables that the path passes through, D n is the density of connection points and cables that the path passes through, A I is the acceleration, which is the speed at which the search agent moves in the search space, aab I and kkb I are the lower and upper limits of acceleration;

[0029] Cable length limit: controlled by the distance of the search agent individual, the formula used is as follows:

[0030]

[0031] in, is the density value at time t+1, is the density value at time t, is the optimal density value found in the current search process, is the volume at time t+1, is the volume at time t, is the optimal volume found in the current search process;

[0032] Balance between global search process and constraints: set temperature factor TF, set maximum number of iterations t of temperature factor max ;

[0033]

[0034] Among them, α is the attenuation factor;

[0035] Step S3: Exploration phase, dynamically adjust the position of the search agent, handle collisions, and introduce randomness and fitness evaluation, specifically including the following:

[0036] When TF≤0.5, a collision occurs between search agent individuals, and the acceleration is recalculated. The acceleration calculation formula is as follows:

[0037]

[0038] in, is the acceleration at time t+1, set and A mr , which are the best historical density, best historical volume and best historical acceleration respectively;

[0039] Perform the initial update, perform a global search, and update the search agent individual based on acceleration. The position update formula of the search agent individual is as follows:

[0040]

[0041] in, is the individual position of the search agent at time t+1, X t is the individual position of the search agent at time t, C1 is the adjustment factor, r is a random number, is the normalized acceleration, d is the distance factor, X rand is the randomly generated search agent individual position, A max and A min The maximum and minimum values ​​of the custom acceleration;

[0042] Step S4: Segment update rules, update the search agent individuals again, update the positions segment by segment based on different conditions, introduce the ranging controller and mutation mechanism, and perform local search. The segment update rules are as follows:

[0043]

[0044] in, The individual position of the search agent at time t+2, ran(1) represents a random number between [0, 1], introducing random perturbations, W1 and W2 are hunger weight coefficients, X z is the best search agent individual position in the current iteration, R is the range controller, r1 and r2 are random integers generated by tent chaotic mapping, l is the weight between global search and local search, and E is the custom offset threshold;

[0045] Game1 is the global search completed by adding a random perturbation, and game2 is the local search that combines the ranging controller to finely adjust the position of the search agent. When r2 > E, the update of the search agent's position biases towards the positive direction of X z , and when r2 < E, it biases towards the reverse direction;

[0046] Step S5: Utilization phase, when there is no collision, adjust the position of the search agent individuals;

[0047] When TF ≤ 0.5, there is no collision between the search agent individuals. At this time, the calculation formula for acceleration is as follows:

[0048]

[0049] The position update formula for the search agent individuals is as follows:

[0050]

[0051] Among them, is the best position in the current iteration, F is the adjustment factor for controlling the update step size, C2 is the control factor for the acceleration contribution degree, r is a random number, T is the custom target position, and X best is the global optimal position, is the best position up to iteration t;

[0052] Step S6: Iterative operation, iterate steps S1 to S5, set the global maximum number of iterations, stop the iteration when the maximum number of iterations is reached, and output the final best position, that is, output the preliminary wiring path.

[0053] The beneficial effects obtained by the present invention using the above scheme are as follows:

[0054] (1) Aiming at the problems of low efficiency, high error rate and poor adaptability in the traditional manual wiring method, the present invention adopts the HGE-ARCO model in the path planning module to generate a preliminary wiring path, quickly adjust the wiring path according to real-time data, use the model to generate the wiring path, reduce the incidence of human errors, and flexibly adjust the wiring path according to the computer room layout and equipment changes;

[0055] (2) The present invention utilizes the population mechanism of the genetic algorithm in the HGE-ARCO model to find a better wiring path. At the same time, it adopts the pheromone concept of the ant colony algorithm, which can dynamically adjust the pheromone concentration according to the performance of the path during the wiring process to guide subsequent path selection. Description of the Drawings

[0056] Figure 1 is a schematic diagram of the automated wiring system for the high-efficiency prefabricated computer room proposed by the present invention;

[0057] Figure 2 A schematic diagram of the process of generating a preliminary wiring path for the HGE-ARCO model proposed in the present invention.

[0058] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention. DETAILED DESCRIPTION

[0059] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only 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 ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0060] Example 1, see Figure 1 The present invention provides an efficient automated wiring system for prefabricated computer rooms, including a wiring planning subsystem, an automated execution subsystem, an intelligent management subsystem, and a data analysis subsystem, specifically including the following contents:

[0061] The wiring planning subsystem includes a data collection module, a path planning module and an optimization strategy module;

[0062] The automated execution subsystem includes an automatic wiring robot and an environment perception module;

[0063] The intelligent management subsystem includes a real-time monitoring module, a fault detection module and an adaptive scheduling module;

[0064] The data analysis subsystem includes a storage module, a data analysis module and a visualization interface.

[0065] Embodiment 2: This embodiment is based on the above embodiment, and the wiring planning subsystem specifically includes the following contents:

[0066] The data collection module collects cabling data, including room layout, equipment location, connection requirements, cable types and length requirements;

[0067] The path planning module generates a preliminary routing path based on the routing data using the HGE-ARCO model;

[0068] The optimization strategy module optimizes the wiring path, obtains the optimal wiring path and converts it into operation instructions;

[0069] The automated execution subsystem includes the following:

[0070] The automatic wiring robot is equipped with a robotic arm, sensors, cameras and a control unit, which lays cables according to the optimal wiring path and operating instructions;

[0071] The environmental perception module collects real-time environmental information through sensors in the automatic wiring robot, including obstacles and position changes of other equipment, and adjusts the optimal wiring path.

[0072] Example 3, see Figure 2 This embodiment is based on the above embodiment. In the path planning module, the HGE-ARCO model is used to generate a preliminary routing path, which specifically includes the following steps:

[0073] Step S1: Initialization, initialize N search agent groups S according to the wiring data I ,The search agent group is composed of individual search agents, and the position of each individual search agent represents a routing path;

[0074] Step S2: defining constraints, including physical limitations of the wiring path, cable length limitations, and connection point requirements;

[0075] Step S3: Exploration phase, dynamically adjust the position of the search agent, handle collisions, and introduce randomness and fitness evaluation;

[0076] Step S4: Update the rules in sections, update the search agent individuals again, update the positions in sections based on different conditions, introduce the ranging controller and mutation mechanism, and perform local search;

[0077] Step S5: During the utilization phase, when no collision occurs, the individual positions of the search agents are adjusted;

[0078] Step S6: iterative operation, iterating step S1 to step S5, setting a global maximum number of iterations, stopping iteration when the maximum number of iterations is reached, and outputting the final optimal position, that is, outputting the preliminary wiring path.

[0079] Embodiment 4: Based on the above embodiment, this embodiment defines constraint conditions, which specifically include the following contents:

[0080] Physical limitations: S I =llb I +rand*(uub I -llb I );

[0081] Among them, S I To search for proxy groups, llb I and uub I are the lower and upper bounds of the search space, and rand is the random number generator;

[0082] Randomly assign volume V o and density D n ;

[0083] Acceleration A I A is randomly generated from the upper and lower limits of acceleration. I The process is as follows:

[0084] A I =aab I +rand*(kkb I -aab I );

[0085] Among them, V o is the number of connection points and cables that the path passes through, D n is the density of connection points and cables that the path passes through, A I is the acceleration, which is the speed at which the search agent moves in the search space, aab I and kkb I are the lower and upper limits of acceleration;

[0086] Cable length limit: controlled by the distance of the search agent individual, the formula used is as follows:

[0087]

[0088] in, is the density value at time t+1, is the density value at time t, is the optimal density value found in the current search process, is the volume at time t+1, is the volume at time t, is the optimal volume found in the current search process;

[0089] Balance between global search process and constraints: set temperature factor TF, set maximum number of iterations t of temperature factor max ;

[0090]

[0091] Among them, α is the attenuation factor.

[0092] In this embodiment, 11b I Set to [0,0,0], the search space starts from the origin of the coordinate system, uub I Set to [100,100,50], the maximum search space is 100m×100m×50m;

[0093] The position of a multi-agent individual in a search is SI =[0,0,0]+0.35*([100,100,50]-[0,0,0]);

[0094] S I =[35,35,17.5];

[0095] This means that the search agent will start path planning at (35, 35, 17.5);

[0096] According to the process of randomly generating acceleration, the randomly obtained A I is 6;

[0097] Volume V o and density D n is the complexity of the connection points and cables in the simulation path, volume V o Represents the number of connection points and cables that the path passes through. The initial value range is [1,50], that is, at least 1 connection point and at most 50 connection points. The density D n Indicates the density of connection points and cables in the area where the path passes, set as a floating point number in the range of [0.1,1.0];

[0098] is 20, is 15, the random number is 0.3, and the formula is used to calculate is 18.5;

[0099] Also calculate the volume is 30;

[0100] Set the attenuation factor α to 0.01 and the maximum number of iterations of the temperature factor t max is 100, then the TF is 0.999 and the temperature factor is close to 1, which means that the search agent can still continue to conduct extensive searches.

[0101] Embodiment 5, based on the above embodiment, this embodiment is in the exploration stage and specifically includes the following contents:

[0102] When TF≤0.5, a collision occurs between search agent individuals, and the acceleration is recalculated. The acceleration calculation formula is as follows:

[0103]

[0104] in, is the acceleration at time t+1, set and A mr , which are the best historical density, best historical volume and best historical acceleration respectively;

[0105] Perform the initial update, perform a global search, and update the search agent individual based on acceleration. The position update formula of the search agent individual is as follows:

[0106]

[0107] in, is the individual position of the search agent at time t+1, X t is the individual position of the search agent at time t, C1 is the adjustment factor, r is a random number, is the normalized acceleration, d is the distance factor, X rand is the randomly generated search agent individual position, A max and A min The maximum and minimum values ​​of the custom acceleration.

[0108] In this embodiment, is 5, is 8, A mr is 3, A max is 10, A min is 1, C1 is set to 1.5, r is set to 0.7, in the initial state, is [30,40,20], t is 0;

[0109] Calculated according to the formula = -0.1079, assuming that the randomly generated search agent individual position X rand is [50,60,30], d is set to 1, The result is [25.468,35.468,17.734].

[0110] Embodiment 6: This embodiment is based on the above embodiment, and the segment update rules are as follows:

[0111]

[0112] in, The individual position of the search agent at time t+2, ran(1) represents a random number between [0, 1], introducing random perturbations, W1 and W2 are hunger weight coefficients, X z is the best search agent individual position in the current iteration, R is the range controller, r1 and r2 are random integers generated by tent chaotic mapping, l is the weight between global search and local search, and E is the custom offset threshold;

[0113] Game1 is a global search with a random perturbation, and game2 is a local search with a range controller to fine-tune the search agent position. When r2>E, the search agent position update is biased towards X. zIn the forward direction, when r2 < R, it is biased in the reverse direction.

[0114] In this embodiment, X z is [30, 40, 20], W1 and W2 are 0.6 and 0.4 respectively, l is set to 0.5, E is defined as 2, ran(1) is 0.2, the random integers r1 and r2 generated by the tent chaotic map are 3 and 4 respectively, and the fixed value R of the ranging controller is 1;

[0115] Since r1 = 3 and l = 0.5, r1 > l;

[0116] Since r2 = 4 and E = 2, r1 < E;

[0117] Therefore, the second case is used for position update: Finally, it is obtained that is [19.8128, 25.8128, 12.9064].

[0118] Embodiment Seven. This embodiment is based on the above embodiment. In the utilization stage, when TF ≤ 0.5, there is no collision between the search agent individuals. At this time, the calculation formula for acceleration is as follows:

[0119]

[0120] The position update formula for the search agent individuals is as follows:

[0121]

[0122] Among them, is the best position in the current iteration, F is the adjustment factor for controlling the update step size, C2 is the control factor for the acceleration contribution degree, r is a random number, T is the user-defined target position, X best is the global optimal position, is the best position up to the t-th iteration.

[0123] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or also includes elements inherent to such process, method, article or device.

[0124] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

[0125] The present invention and its embodiments are described above, and such description is not restrictive. The drawings show only one embodiment of the present invention, and the actual structure is not limited thereto. In short, if ordinary technicians in the field are inspired by it, without departing from the purpose of the invention, they can design a structure and embodiment similar to the technical solution without creativity, which should belong to the protection scope of the present invention.

Claims

1. The automated wiring system for efficient prefabricated computer rooms is characterized by: It includes wiring planning subsystem, automatic execution subsystem, intelligent management subsystem and data analysis subsystem, specifically including the following contents: The wiring planning subsystem includes a data collection module, a path planning module and an optimization strategy module; The automated execution subsystem includes an automatic wiring robot and an environment perception module; The intelligent management subsystem includes a real-time monitoring module, a fault detection module and an adaptive scheduling module; The data analysis subsystem includes a storage module, a data analysis module and a visualization interface; The wiring planning subsystem includes a data collection module, a path planning module and a route planning module, which specifically include the following contents: The data collection module collects cabling data, including room layout, equipment location, connection requirements, cable types and length requirements; The path planning module generates a preliminary routing path based on the routing data using the HGE-ARCO model; The optimization strategy module optimizes the wiring path, obtains the optimal wiring path and converts it into operation instructions; Furthermore, the automated execution subsystem includes an automatic wiring robot and an environmental perception module, specifically including the following: The automatic wiring robot is equipped with a robotic arm, sensors, cameras and a control unit, which lays cables according to the optimal wiring path and operating instructions; The environmental perception module collects real-time environmental information through sensors in the automatic wiring robot, including obstacles and position changes of other equipment, and adjusts the optimal wiring path.

2. The automated wiring system for a high-efficiency prefabricated computer room according to claim 1 is characterized in that: In the path planning module, the HGE-ARCO model is used to generate a preliminary routing path, which includes the following steps: Step S1: Initialization, initialize N search agent groups S according to the wiring data I ,The search agent group is composed of individual search agents, and the position of each individual search agent represents a routing path; Step S2: defining constraints, including physical limitations of the wiring path, cable length limitations, and connection point requirements; Step S3: Exploration phase, dynamically adjust the position of the search agent, handle collisions, and introduce randomness and fitness evaluation; Step S4: Update the rules in sections, update the search agent individuals again, update the positions in sections based on different conditions, introduce the ranging controller and mutation mechanism, and perform local search; Step S5: During the utilization phase, when no collision occurs, the individual positions of the search agents are adjusted; Step S6: iterative operation, iterating step S1 to step S5, setting a global maximum number of iterations, stopping iteration when the maximum number of iterations is reached, and outputting the final optimal position, that is, outputting the preliminary wiring path.

3. The automated wiring system for a high-efficiency prefabricated computer room according to claim 2 is characterized in that: Step S2, defining constraints, specifically including the following: Define constraints, including the following: Physical limitations: S I =llb I +rand*(uub I -llb I ); Among them, S I To search for proxy groups, llb I and uub I are the lower and upper bounds of the search space, and rand is the random number generator; Randomly assign volume V o and density D n ; Acceleration A I A is randomly generated from the upper and lower limits of acceleration. I The process is as follows: <h2 style=";text-align:left;direction:ltr">A<h2 style=";text-align:left;direction:ltr"> I <h2 style=";text-align:left;direction:ltr"> (aab)<h2 style=";text-align:left;direction:ltr"> I <h2 style=";text-align:left;direction:ltr"> +rand*(kkb<h2 style=";text-align:left;direction:ltr"> I <h2 style=";text-align:left;direction:ltr"> -aab<h2 style=";text-align:left;direction:ltr"> I <h2 style=";text-align:left;direction:ltr"> ); Among them, V o is the number of connection points and cables that the path passes through, D n is the density of connection points and cables that the path passes through, A I is the acceleration, which is the speed at which the search agent moves in the search space, aab I and kkb I are the lower and upper limits of acceleration; Cable length limit: controlled by the distance of the search agent individual, the formula used is as follows: in, is the density value at time t+1, is the density value at time t, is the optimal density value found in the current search process, is the volume at time t+1, is the volume at time t, is the optimal volume found in the current search process; Balance between global search process and constraints: set temperature factor TF, set maximum number of iterations t of temperature factor max ; Among them, α is the attenuation factor.

4. The automated wiring system for a high-efficiency prefabricated computer room according to claim 2 is characterized in that: Step S3, the exploration phase, specifically includes the following contents: When TF≤0.5, a collision occurs between search agent individuals, and the acceleration is recalculated. The acceleration calculation formula is as follows: in, is the acceleration at time t+1, set and A mr , which are the best historical density, best historical volume and best historical acceleration respectively; Perform the initial update, perform a global search, and update the search agent individual based on acceleration. The position update formula of the search agent individual is as follows: in, is the individual position of the search agent at time t+1, X t is the individual position of the search agent at time t, C1 is the adjustment factor, r is a random number, is the normalized acceleration, d is the distance factor, X rand is the randomly generated search agent individual position, A max and A min The maximum and minimum values ​​of the custom acceleration.

5. The automated wiring system for a high-efficiency prefabricated computer room according to claim 2 is characterized in that: Step S4, the segment update rules are as follows: in, The search agent individual position at time t+2, ran(1) represents a random number between the interval [0, 1], introducing random perturbations, W1 and W2 are hunger weight coefficients, X z is the best search agent individual position in the current iteration, R is the range controller, r1 and r2 are random integers generated by tent chaotic mapping, l is the weight between global search and local search, and E is the custom offset threshold; Game1 is the global search completed by adding a random perturbation, and game2 is the local search that combines the ranging controller to finely adjust the position of the search agent. When r2 > E, the update of the search agent's position biases towards the positive direction of X z , and when r2 < E, it biases towards the reverse direction.

6. The automated wiring system for a high-efficiency prefabricated computer room according to claim 2 is characterized in that: Step S5, the utilization stage, when TF≤0.5, there is no collision between the search agent individuals, and the acceleration calculation formula is as follows: The position update formula of the search agent individual is as follows: in, is the best position in the current iteration, F is the adjustment factor for controlling the update step size, C2 is the control factor for the acceleration contribution, r is a random number, T is the custom target position, and X best is the global optimal position, is the best position after iteration up to t.

Images