Fault early warning and conversion rescue method and device based on intelligent manufacturing equipment

Abstract

The invention discloses a fault early warning and conversion rescue method and device based on intelligent manufacturing equipment, and the method comprises the following steps: continuously collecting the operation parameters and health state data of the intelligent production equipment through a multi-type sensor array, recording the influence of a disposal means on the health state of the equipment, constructing and dynamically updating a fault data set and a normal data set; the database parameters are classified according to the parameter classification standard, adjustable parameters and non-adjustable parameters are divided, and conversion difficulty coefficients of the adjustable parameters are set; calculating an expected conversion rate based on the fault solution rate corresponding to the optional value of the adjustable parameter; constructing a conversion tree with non-adjustable parameters as root nodes and adjustable parameters as branches by adopting an information gain rate priority principle, and performing pruning optimization; traversing leaf branch nodes of the conversion tree for the input scheme to generate a conversion scheme set; and the conversion scheme is converted into a form convenient for the management personnel to read and is provided for production managers.

Description

Technical Field

[0001] The present invention relates to the field of data mining and intelligent strategy generation, and in particular, to a fault warning and conversion rescue method and device based on intelligent manufacturing equipment. Background Art

[0002] In the current era of rapid development of intelligent manufacturing, intelligent production equipment is widely used in various industries and has become a key factor in improving production efficiency and ensuring product quality. However, once an intelligent production equipment fails, it may lead to a series of serious problems such as production interruption, increased costs, and delivery delays. Currently, in terms of fault warning of intelligent production equipment, the more commonly used technical means is usually the physical parameter analysis method based on sensor monitoring. By collecting and analyzing key physical parameters such as the temperature, pressure, and vibration of the equipment in real time, a warning signal is issued when the parameters exceed the normal threshold range.

[0003] At the same time, machine learning algorithms based on data-driven are also widely used in fault warning. Algorithms such as support vector machines and decision trees learn from a large amount of historical fault data and normal operation data to build a fault prediction model, so as to judge whether the current operating state of the equipment tends to fail.

[0004] In terms of generating disposal strategies, some enterprises adopt a method based on a rule library. A series of processing rules for different fault types are formulated in advance. When a fault warning occurs, the system matches the corresponding disposal strategy from the rule library according to the identified fault type, such as restarting the equipment, replacing specific parts, etc.

[0005] However, the existing methods have certain limitations. The method based on sensor monitoring has insufficient sensitivity to some early potential faults and may not be able to detect subtle performance changes in time. Although machine learning algorithms have high prediction accuracy, they have extremely high requirements for data quality. If the data has noise or incompleteness, it will seriously affect the reliability of the model. The method for generating disposal strategies based on a rule library lacks flexibility and is difficult to handle complex and changeable, unforeseen fault scenarios, and cannot adjust and optimize the disposal plan in real time according to the actual situation.

[0006] In view of this, it is particularly important to explore a new data mining method for obtaining dynamic conversion of the state of things that can fill the above gaps. This method not only needs to be able to systematically compare the similarities and differences between different schemes, reveal the internal connections and conversion laws between them, but also distinguish the parameter adjustability, so as to flexibly adjust the mining strategy according to the specific application scenario and data characteristics, so as to obtain more accurate and comprehensive state change analysis results.

[0007] Prior art discloses a method for mining knowledge about the dynamic transformation of object states based on artificial intelligence technology. This method uses a weighted calculation method based on information gain and the degree of variable transformability to construct an initial transformation tree, evaluate and prune the tree, and then determine a parameter adjustment strategy for object state transformation. Finally, the optimized parameter settings are implemented and feedback is provided. This method can be widely used in fault warning and rescue strategy generation for intelligent production equipment. Summary of the Invention

[0008] To address the technical problem in the prior art of fault warning and rescue strategy generation, which involves only making predictions and rigidly processing according to established solutions without distinguishing parameter adjustability to avoid recurrence of the same fault, the present invention provides a fault warning and conversion rescue method and device based on intelligent manufacturing equipment. The technical solution adopted by the present invention is:

[0009] A first aspect of the present invention provides a fault warning and conversion rescue method based on intelligent manufacturing equipment, comprising the following steps:

[0010] S1: Continuously collect operating parameters and health status data of intelligent production equipment through a multi-type sensor array, record the impact of treatment measures on the health status of equipment, and build and dynamically update fault data sets and normal data sets;

[0011] S2: Classify the database parameters according to the preset parameter classification standard, divide them into adjustable parameters and non-adjustable parameters, and set the conversion difficulty coefficient of the adjustable parameters;

[0012] S3: Calculate the expected conversion rate based on the fault resolution rate corresponding to the optional value of the adjustable parameter;

[0013] S4: Adopting the information gain rate priority principle, a transformation tree is constructed with non-adjustable parameters as root nodes and adjustable parameters as branches, and pruning optimization is performed;

[0014] S5: Traverse the leaf branch nodes of the transformation tree for the input solution and generate a multi-dimensional transformation solution set;

[0015] S6: Converting the obtained conversion plan into a form that is easy for management personnel to read and providing it to production managers is a preferred solution. In step S1, the multi-type sensor array includes:

[0016] A rotating machinery vibration monitoring unit composed of a piezoelectric acceleration sensor and a stress wave sensor;

[0017] Power equipment monitoring unit composed of current sensor, infrared sensor and partial discharge sensor;

[0018] Fluid medium parameter monitoring module composed of automated instrument units;

[0019] The health status data includes fault types, faulty components, and predicted remaining life values, where the fault types cover three categories: mechanical faults, electrical faults, and compound faults, and the faulty components specifically include at least one of bearing assemblies, gear sets, rotor systems, and motor stators and rotors.

[0020] As a preferred solution, in the step S2, the preset parameter classification criteria include:

[0021] The determination condition for adjustable parameters is that the parameter value can be adjusted online and the core function of the equipment is not affected after adjustment;

[0022] The value range of the conversion difficulty coefficient is [0, 1].

[0023] As a preferred solution, in the step S3, the calculation formula for the expected conversion rate is as follows:

[0024] Expected conversion rate E(A) = Average(E + (A i ))

[0025]

[0026] Among them, for parameter A, is the average of all non - negative values, is the expected conversion rate after the parameter is adjusted from the i - th optional value to the j - th optional value, P(A i ) is the frequency of the i - th optional value, P(A i →B) is the target frequency reached by the i - th optional value, is the confidence level of the j - th optional value, is the non - target frequency of the i - th optional value.

[0027] As a preferred solution, in the step S4, the conversion tree construction method includes:

[0028] S401: Obtain non - adjustable parameters as the root nodes. When there are multiple non - adjustable parameters, calculate the information gain rate of each parameter and construct a multi - level root node system in descending order; at the same time, arrange the adjustable parameters in ascending order of the expected conversion rate to generate an adjustable parameter sequence;

[0029] S402: Select the adjustable parameter with the highest current priority from the adjustable parameter sequence in turn as the first adjustment variable;

[0030] S403: Based on all the optional values of the first adjustment variable, generate sub - node branches with corresponding numerical ranges from the end nodes of each root node group;

[0031] S404: Update the newly generated sub - node set as the current root node group;

[0032] S405: Loop and execute steps S402 - S404 until all parameters in the adjustable parameter sequence are traversed;

[0033] S406: Adopt a combined strategy of pre - pruning and post - pruning to optimize the structure of the generated transformation tree.

[0034] As a preferred solution, in the said step S5, the solution generation method includes:

[0035] S501: Take the leaf node of the corresponding tree branch of the solution as the second node;

[0036] S502: Take the parent node corresponding to the second node as the third node; and take the nodes in the children nodes of the third node except the second node as the child node group;

[0037] S503: Judge whether there is a node in the child node group; if so, execute step S504; if not, execute step S506;

[0038] S504: Select a node in the child node group as the first node, and replace the parameter optional value corresponding to the second node in the solution with the parameter optional value represented by the first node to form a new solution;

[0039] S505: Remove the first node from the child node group, and execute step S503;

[0040] S506: Judge whether the third node is the root node; if so, execute step S508; if not, execute step S507;

[0041] S507: Take the third node as the new second node, and take the parent node of this third node as the new third node; take the nodes in the children nodes of the new third node except the new second node as the new child node group; execute step S503;

[0042] S508: Take the obtained new solution as the transformation solution.

[0043] As a preferred solution, in the said step S2, the adjustable parameters include vibration, temperature, humidity, pressure, voltage, current, flow rate, and concentration; the non - adjustable parameters include the degree of wear, the used time, and the design life.

[0044] The second aspect of the present invention provides a fault warning and transformation rescue device for implementing the foregoing method, including a database establishment module, a parameter identification and division module, an expected conversion rate calculation module, a transformation tree construction module, a traversal transformation tree module, and a solution output module;

[0045] The database establishment module is used to continuously collect the operation parameters and health status data of intelligent production equipment through a multi-type sensor array, record the impact of disposal means on the equipment health status, and construct and dynamically update the fault data set and normal data set;

[0046] The parameter identification and classification module is used to classify the database parameters according to the preset parameter classification standard, divide the adjustable parameters and non-adjustable parameters, and set the conversion difficulty coefficient of the adjustable parameters;

[0047] The expected conversion rate calculation module is used to calculate the expected conversion rate based on the fault resolution rate corresponding to the optional values of the adjustable parameters;

[0048] The conversion tree construction module is used to construct a conversion tree with non-adjustable parameters as the root node and adjustable parameters as the branches by adopting the principle of giving priority to the information gain rate, and perform pruning optimization;

[0049] The traversing conversion tree module is used to traverse the leaf branch nodes of the conversion tree for the input scheme to generate a multi-dimensional conversion scheme set;

[0050] The scheme output module is used to convert the obtained conversion scheme into a form convenient for management personnel to read and provide it to the production manager.

[0051] The third aspect of the present invention provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the foregoing fault warning and conversion rescue method based on intelligent manufacturing equipment are implemented.

[0052] The fourth aspect of the present invention provides a computer device, including a storage medium, a processor, and a computer program stored in the storage medium and executable by the processor. When the computer program is executed by the processor, the steps of the foregoing fault warning and conversion rescue method based on intelligent manufacturing equipment are implemented.

[0053] Compared with the prior art, the beneficial effects of the present invention are:

[0054] The present invention arranges and generates a parameter sequence according to the importance and convertibility of the parameters, constructs a conversion tree based on the parameter sequence, and generates a new conversion scheme through traversing the conversion tree. Specific optimization measures can be provided to the production manager before a specific fault occurs, so as to avoid the occurrence of faults at a lower cost. Generally speaking, the scheme generated by the present invention can better adapt to the data mining of structured and unstructured data sets of various intelligent manufacturing equipment, and generate fault warning and fault conversion strategies based on this. Description of the Drawings

[0055] Figure 1Flowchart of a fault warning and conversion rescue method based on intelligent manufacturing equipment provided in this embodiment;

[0056] Figure 2 Schematic diagram of the module connection of the fault warning and conversion rescue device provided in this embodiment. Detailed implementation manners

[0057] The drawings are only for illustrative purposes and should not be construed as limitations on the present invention;

[0058] It should be clear that the described embodiments are only a part of the embodiments of the present application, rather than all of them. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope protected by the embodiments of the present application.

[0059] The terms used in the embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to limit the embodiments of the present application. The singular forms "a", "the" and "said" used in the embodiments of the present application and the appended claims are also intended to include the plural forms, unless the context clearly indicates otherwise. It should also be understood that the term " / and / " as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0060] When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The implementation manners described in the following exemplary embodiments do not represent all implementation manners consistent with the present application. On the contrary, they are only examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims. In the description of the present application, it should be understood that the terms "first", "second", "third", etc. are only used to distinguish similar objects, and do not have to be used to describe a specific order or sequence, nor can they be understood as indicating or implying relative importance. For those of ordinary skill in the art, the specific meanings of the above terms in the present application can be understood according to specific circumstances.

[0061] In addition, in the description of the present application, unless otherwise specified, "a plurality of" means two or more. " / and / " describes the association relationship of associated objects and indicates that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. The character " / " generally represents an "or" relationship between the front and back associated objects. The following further elaborates on the present invention with reference to the drawings and embodiments.

[0062] The following further elaborates on the present invention with reference to the drawings and embodiments.

[0063] Embodiment 1

[0064] Please refer to Figure 1 , this embodiment provides a fault warning and conversion rescue method based on intelligent manufacturing equipment, including the following steps:

[0065] S1: Continuously collect the operation parameters and health status data of intelligent production equipment through a multi-type sensor array, record the impact of disposal means on the equipment health status, and construct and dynamically update the fault data set and normal data set;

[0066] In a specific embodiment, in the step S1, the multi-type sensor array includes:

[0067] A rotating machinery vibration monitoring unit composed of a piezoelectric acceleration sensor and a stress wave sensor;

[0068] A power equipment monitoring unit composed of a current sensor, an infrared sensor, and a partial discharge sensor;

[0069] A fluid medium parameter monitoring module composed of an automation instrument unit;

[0070] The health status data includes fault type, fault component, and remaining life prediction value, where the fault type covers three categories: mechanical fault, electrical fault, and composite fault, and the fault component specifically includes at least one of a bearing assembly, a gear set, a rotor system, and a motor stator and rotor.

[0071] Specifically, in the step S1, the parameters and acquisition means involved include, but are not limited to: using piezoelectric acceleration sensors and stress wave sensors to acquire vibration and shock parameters of rotating machinery and equipment; using current sensors, infrared sensors, etc. to acquire parameters such as temperature, humidity, pressure, partial discharge, current, voltage, infrared, gas content, etc. of power equipment; using automated instrument units to acquire parameters such as temperature, humidity, pressure, flow rate, particle size, concentration, etc. of fluid energy media. Record the health status, fault location, fault type, and faulty components, and deduce the remaining life based on the continuously recorded data. The fault types include, but are not limited to, bearings, gears, rotors, motor electrical types, and composites. Faulty components include, but are not limited to: outer ring, inner ring, rolling element, and cage faults in bearing faults; wear, spalling, cracks, missing teeth, broken teeth, etc. in gear faults; blade imbalance, overall imbalance, misalignment, and shaft bending in rotor faults; motor bar breakage, open phase, voltage imbalance, short circuit, etc. in motor electrical faults. This acquisition method needs to implement various key parameters that have a greater impact on the use of the equipment, and divide them into adjustable parameters and non-adjustable parameters for storage and recording. When the equipment starts working, whenever a fault occurs in the equipment, it is necessary to record the parameter values at the time of the fault, and at the same time collect the fault occurrence time, fault location, fault type, faulty components, and specific values of each parameter as a control group. During the normal operation of the equipment, whenever the equipment parameters change, if the equipment can still continue to work normally, it is necessary to record this set of parameters to enrich the database data set. On this basis, we can establish two large data sets, namely the fault data set and the normal data set, and based on these two large data sets, provide a basis for the construction of the transformation tree and the generation of strategies..

[0072] S2: Classify the database parameters according to the preset parameter classification standard, divide them into adjustable parameters and non-adjustable parameters, and set the conversion difficulty coefficient of the adjustable parameters;

[0073] In a specific embodiment, the preset parameter classification standard includes:

[0074] The determination condition for adjustable parameters is that the parameter value can be adjusted online and does not affect the core function of the equipment after adjustment;

[0075] The value range of the conversion difficulty coefficient is [0, 1].

[0076] S3: Calculate the expected conversion rate based on the fault resolution rate corresponding to the optional values of the adjustable parameters;

[0077] In a specific embodiment, in the step S3, the calculation formula for the expected conversion rate is as follows:

[0078] Expected conversion rate E(A) = Average(E + (Ai ))

[0079]

[0080] Among them, for parameter A, which is the average value of all non - negative values, is the expected conversion rate after the parameter is adjusted from the i - th optional value to the j - th optional value, P(A i ) is the frequency of the i - th optional value, P(A i →B) is the target frequency reached by the i - th optional value, is the confidence level of the j - th optional value, is the frequency of the i - th optional value that fails to reach the target.

[0081] S4: Construct a conversion tree with non - adjustable parameters as the root nodes and adjustable parameters as the branches according to the principle of giving priority to the information gain ratio, and perform pruning optimization;

[0082] In a specific embodiment, in the step S4, the method for constructing the conversion tree includes:

[0083] S401: Obtain non - adjustable parameters as the root nodes. When there are multiple non - adjustable parameters, calculate the information gain ratio of each parameter and construct a multi - level root node system in descending order; at the same time, arrange the adjustable parameters in ascending order of the expected conversion rate to generate an adjustable parameter sequence;

[0084] S402: Select the currently highest - priority adjustable parameter from the adjustable parameter sequence as the first adjustment variable in turn;

[0085] S403: Based on all the optional values of the first adjustment variable, generate sub - node branches with corresponding numerical ranges from the end nodes of each root node group;

[0086] S404: Update the newly generated sub - node set as the current root node group;

[0087] S405: Loop through steps S402 - S404 until all the parameters in the adjustable parameter sequence are traversed;

[0088] S406: Optimize the structure of the generated conversion tree by combining pre - pruning and post - pruning strategies.

[0089] S5: Traverse the leaf - branch nodes of the conversion tree for the input scheme to generate a multi - dimensional conversion scheme set;

[0090] In a specific embodiment, in the step S5, the method for generating the scheme includes:

[0091] S501: Take the leaf nodes of the corresponding tree branch of the scheme as the second nodes;

[0092] S502: Use the parent node corresponding to the second node as the third node; use the nodes in the children nodes of the third node excluding the second node as the child node group;

[0093] S503: Determine whether there are nodes in the child node group; if so, execute step S504; if not, execute step S506;

[0094] S504: Select a node in the child node group as the first node, and replace the parameter optional value corresponding to the second node in the parameter optional value replacement scheme represented by the first node to form a new scheme;

[0095] S505: Remove the first node from the child node group and execute step S503;

[0096] S506: Determine whether the third node is the root node; if so, execute step S508; if not, execute step S507;

[0097] S507: Use the third node as the new second node, and use the parent node of this third node as the new third node; use the nodes in the children nodes of the new third node excluding the new second node as the new child node group; execute step S503;

[0098] S508: Use the obtained new scheme as the conversion scheme.

[0099] In a specific embodiment, in the step S2, the adjustable parameters include vibration, temperature, humidity, pressure, voltage, current, flow rate, and concentration; the non-adjustable parameters include the degree of wear, the service time, and the design life.

[0100] S6: Convert the obtained conversion scheme into a form convenient for management personnel to read and provide it to the production manager.

[0101] Embodiment 2

[0102] Please refer to Figure 2 , this embodiment provides a fault warning and conversion rescue device for implementing the method described in Embodiment 1, including a database establishment module, a parameter identification and division module, an expected conversion rate calculation module, a conversion tree construction module, a traversal conversion tree module, and a scheme output module;

[0103] The database establishment module is used to continuously collect the operation parameters and health status data of intelligent production equipment through a multi-type sensor array, record the impact of disposal means on the equipment health status, and construct and dynamically update the fault data set and the normal data set;

[0104] The parameter identification and division module is used to classify the database parameters according to a preset parameter classification standard, divide the adjustable parameters and the non-adjustable parameters, and set the conversion difficulty coefficient of the adjustable parameters;

[0105] The expected conversion rate calculation module is used to calculate the expected conversion rate based on the failure resolution rate corresponding to the optional values of the adjustable parameters;

[0106] The conversion tree construction module is used to construct a conversion tree with non-adjustable parameters as the root nodes and adjustable parameters as the branches by adopting the principle of giving priority to the information gain ratio, and perform pruning optimization;

[0107] The traversing conversion tree module is used to traverse the leaf branch nodes of the conversion tree for the input scheme to generate a multi-dimensional conversion scheme set;

[0108] The scheme output module is used to convert the obtained conversion scheme into a form convenient for managers to read and provide it to the production manager.

[0109] Embodiment 3

[0110] A computer-readable storage medium stores a computer program thereon. When the computer program is executed by a processor, the steps of a method for fault warning and conversion rescue based on intelligent manufacturing equipment described in Embodiment 1 are implemented.

[0111] Embodiment 4

[0112] A computer device includes a storage medium, a processor, and a computer program stored in the storage medium and executable by the processor. When the computer program is executed by the processor, the steps of a method for fault warning and conversion rescue based on intelligent manufacturing equipment described in Embodiment 1 are implemented.

[0113] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the present invention, rather than limiting the implementation manners of the present invention. For those of ordinary skill in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to enumerate all the implementation manners here. Any modifications, equivalent replacements, and improvements made within the spirit and principle of the present invention shall be included in the protection scope of the claims of the present invention.

Claims

1. A fault warning and conversion rescue method based on intelligent manufacturing equipment, characterized in that, It includes the following steps: S1: Continuously collect the operation parameters and health status data of intelligent production equipment through a multi-type sensor array, record the impact of disposal means on the equipment health status, and construct and dynamically update the fault data set and normal data set; S2: Classify the database parameters according to the preset parameter classification standard, divide them into adjustable parameters and non-adjustable parameters, and set the conversion difficulty coefficient of the adjustable parameters; S3: Calculate the expected conversion rate based on the fault resolution rate corresponding to the optional values of the adjustable parameters; S4: Construct a conversion tree with non-adjustable parameters as the root nodes and adjustable parameters as the branches according to the information gain rate priority principle, and perform pruning optimization; S5: Traverse the leaf branch nodes of the conversion tree for the input scheme to generate a multi-dimensional conversion scheme set; S6: Convert the obtained conversion scheme into a form convenient for managers to read and provide it to production managers.

2. The method according to claim 1, characterized in that, In the step S1, the multi-type sensor array includes: A rotating machinery vibration monitoring unit composed of a piezoelectric acceleration sensor and a stress wave sensor; An electrical equipment monitoring unit composed of a current sensor, an infrared sensor, and a partial discharge sensor; A fluid medium parameter monitoring module composed of an automation instrument unit; The health status data includes fault type, fault component, and remaining life prediction value, where the fault type covers three categories: mechanical fault, electrical fault, and composite fault, and the fault component specifically includes at least one of a bearing assembly, a gear set, a rotor system, and a motor stator and rotor.

3. The method according to claim 1, wherein In the step S2, the preset parameter classification standard includes: The determination condition for adjustable parameters is that the parameter value can be adjusted online and does not affect the core function of the equipment after adjustment; The value range of the conversion difficulty coefficient is [0,1].

4. The method according to claim 1, wherein In the step S3, the calculation formula for the expected conversion rate is as follows: Expected conversion rate E(A) = Average(E + (A i )) Among them, for parameter A, which is the average of all non - negative values, is the expected conversion rate after the parameter is adjusted from the i - th optional value to the j - th optional value, P(A i ) is the frequency of the i - th optional value, P(A i →B) is the achieved target frequency of the i - th optional value, is the confidence level of the j - th optional value, is the un - achieved target frequency of the i - th optional value.

5. The method according to claim 1, characterized in that, In the step S4, the method for constructing the conversion tree includes: S401: Obtain non-adjustable parameters as root nodes. When there are multiple non-adjustable parameters, calculate the information gain rate of each parameter and construct a multi-level root node system in descending order; at the same time, arrange the adjustable parameters in ascending order of the expected conversion rate to generate an adjustable parameter sequence; S402: Select the adjustable parameter with the highest current priority from the adjustable parameter sequence as the first adjustment variable in turn; S403: Based on all optional values of the first adjustment variable, generate sub-node branches with corresponding numerical ranges from the end nodes of each root node group; S404: Update the newly generated sub-node set as the current root node group; S405: Loop through steps S402 - S404 until all parameters in the adjustable parameter sequence are traversed; S406: Optimize the structure of the generated conversion tree by combining pre-pruning and post-pruning strategies.

6. The method according to claim 1, characterized in that, In the step S5, the method for generating the scheme includes: S501: Take the leaf nodes of the corresponding tree branch of the scheme as the second nodes; S502: Take the parent nodes corresponding to the second nodes as the third nodes; and take the nodes in the sub-nodes of the third nodes except the second nodes as the sub-node group; S503: Determine whether there are nodes in the sub-node group; if so, execute step S504; if not, execute step S506; S504: Select a node from the sub-node group as the first node, and replace the parameter alternative value corresponding to the second node in the parameter alternative value solution represented by the first node to form a new solution. S505: Remove the first node from the sub-node group, and execute step S503. S506: Determine whether the third node is the root node; if so, execute step S508; if not, execute step S507. S507: Take the third node as the new second node, and take the parent node of the third node as the new third node; take the nodes in the sub-nodes of the new third node except the new second node as the new sub-node group; execute step S503. S508: Take the obtained new solution as the transformation solution.

7. The method according to claim 1, wherein In the step S2, the adjustable parameters include vibration, temperature, humidity, pressure, voltage, current, flow rate, and concentration; the non-adjustable parameters include the degree of wear, the used time, and the design life.

8. A fault warning and conversion rescue device for implementing the method according to any one of claims 1-7, characterized in that, It includes a database establishment module, a parameter identification and division module, an expected conversion rate calculation module, a conversion tree construction module, a traversal conversion tree module, and a solution output module. The database establishment module is used to continuously collect the operation parameters and health status data of intelligent production equipment through a multi-type sensor array, record the impact of disposal means on the equipment health status, and construct and dynamically update the fault data set and the normal data set. The parameter identification and division module is used to classify the database parameters according to the preset parameter classification standard, divide the adjustable parameters and the non-adjustable parameters, and set the conversion difficulty coefficient of the adjustable parameters. The expected conversion rate calculation module is used to calculate the expected conversion rate based on the fault resolution rate corresponding to the alternative values of the adjustable parameters. The conversion tree construction module is used to construct a conversion tree with non-adjustable parameters as the root node and adjustable parameters as the branches by adopting the principle of giving priority to the information gain rate, and perform pruning optimization. The traversal conversion tree module is used to traverse the leaf branch nodes of the conversion tree for the input solution to generate a multi-dimensional conversion solution set. The solution output module is used to convert the obtained conversion solution into a form convenient for management personnel to read and provide it to the production manager.

9. A computer-readable storage medium storing a computer program thereon, characterized in that: When the computer program is executed by the processor, it realizes the steps of a fault warning and conversion rescue method based on intelligent manufacturing equipment as described in any one of claims 1 to 7.

10. A computer device, characterized in that: It includes a storage medium, a processor, and a computer program stored in the storage medium and executable by the processor. When the computer program is executed by the processor, it realizes the steps of a fault warning and conversion rescue method based on intelligent manufacturing equipment as described in any one of claims 1 to 7.

Images