Disclosure of Invention
The invention aims to solve at least one technical problem in the prior art, and provides a method, a device, equipment and a storage medium for analyzing the failure of a heating surface of a power plant. A strong association relation between the attribute information of the heating surface of the power plant and a metal failure mode is established based on an FP-Growth algorithm, a reliable association rule is extracted, a failure warning effect is provided for metal equipment with similar characteristics in an in-service unit, the purpose of predicting equipment failure is achieved, and the metal equipment failure is prevented.
As an optional implementation manner, the present disclosure discloses a method for analyzing failure of a heating surface of a power plant, including the following steps:
extracting power plant heating surface attribute information from a power plant heating surface inspection report, and performing discretization processing on the power plant heating surface attribute information;
calculating strong association relations between all attributes in the attribute information of the heating surface of the power plant and metal failure forms according to an FP-Growth algorithm and establishing association rules;
sorting the association rules in a descending order according to the confidence coefficient, and dividing a plurality of association rules into an early warning set;
and matching the data of the heating surface of the power plant to be detected with the association rule, and if the matched association rule item is in the early warning set, sending an early warning signal.
As an alternative implementation, the present disclosure discloses a failure analysis device for a heating surface of a power plant, including:
the system comprises a data extraction module, a data association calculation module, a data sorting module and a data matching early warning module;
the data extraction module is used for extracting power plant heating surface attribute information from a power plant heating surface inspection report and carrying out discretization processing on the power plant heating surface attribute information;
the data association calculation module is used for calculating a strong association relation between each attribute in the attribute information of the heating surface of the power plant and a metal failure mode according to an FP-Growth algorithm and establishing an association rule;
the data sorting module is used for sorting the association rules in a descending order according to the confidence degrees and dividing a plurality of previous association rules into an early warning set;
the data matching early warning module is used for matching the data of the heating surface of the power plant to be detected with the association rule, and if the matched association rule item is in the early warning set, an early warning signal is sent out.
As an alternative implementation, the present disclosure discloses a power plant heating surface failure analysis apparatus, including: at least one control processor and a memory for communicative connection with the at least one control processor; the memory stores instructions executable by the at least one control processor to enable the at least one control processor to perform a method of power plant heating surface failure analysis as described above.
As an alternative implementation, the present disclosure discloses a computer-readable storage medium storing computer-executable instructions for causing a computer to perform a method of power plant heating surface failure analysis as described above.
Compared with the prior art, the technical scheme disclosed by the embodiment of the disclosure has the following advantages:
the scheme disclosed by the invention is based on a data analysis method, assists in the supervision work of metal failure and provides early warning for possible failure of the heating surface. Aiming at data in a power plant heating surface inspection report, a strong association relation between power plant heating surface attribute information and a metal failure form is established based on an FP-Growth algorithm, a reliable association rule is extracted, a failure warning effect is provided for metal equipment with similar characteristics in an in-service unit, the purpose of predicting equipment failure is achieved, and the metal equipment failure is prevented.
Further features and advantages realized by the embodiments of the present disclosure will be set forth in the detailed description or may be learned by the practice of the embodiments.
Detailed Description
The technical solutions of the embodiments of the present disclosure will be described clearly and completely with reference to the accompanying drawings, and it is to be understood that the described embodiments are only a part of the embodiments of the present disclosure, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the disclosure without making any creative effort, shall fall within the protection scope of the disclosure. It should be noted that the features of the embodiments and examples of the present disclosure may be combined with each other without conflict. In addition, the purpose of the drawings is to graphically supplement the description in the written portion of the specification so that a person can intuitively and visually understand each technical feature and the whole technical solution of the present disclosure, but it should not be construed as limiting the scope of the present disclosure.
Referring to fig. 1, in an alternative embodiment, a method for analyzing failure of a heating surface of a power plant is provided, which includes the following steps:
s101, extracting power plant heating surface attribute information from a power plant heating surface inspection report, and performing discretization processing on the power plant heating surface attribute information;
the inspection report of the heating surface of the power plant is from the inspection report of the heating surface of the power plant by an electric academy, wherein each inspection report comprises detection data of metal failure of equipment of a manufacturer;
preferably, the extracted attributes of the heating surface of the power plant include: material (CZ), diameter (ZJ), thickness (HD), inner/outer three rings (NW), capacity grade (RL), manufacturer (CJ), run coal (MZ), accumulated run time (YX), accumulated over-temperature time (CW), aging grade (LH), scale thickness (YHP), and metal failure mode (XY).
In the step, the attributes of the heating surface of the power plant are extracted from a plurality of inspection reports, and discretization is carried out on the attributes to facilitate subsequent processing, wherein the preferable discretization is as follows:
discrete numerical value conversion is carried out on the material, the inner circle, the outer circle, the manufacturer, the operation coal type and the metal failure mode according to the attributes; and (3) carrying out numerical dispersion on the diameter, the thickness, the capacity grade, the accumulated running time, the accumulated overtemperature time, the aging grade and the oxide skin thickness by adopting an equal width method, and reducing the computational complexity, such as: for classification variables such as material, inner/outer three circles, manufacturers, operating coal types and metal failure modes, the classified numerical values can be directly utilized and can be directly converted into [0, 1, 2, 3 … N ]; the running time is accumulated and divided into six equal-width bins of [0, 20000], [20000, 40000], [40000, 60000], [60000, 80000], [80000, 100000, ∞ ], and then mapped to [0, 1, 2, 3, 4, 5], respectively.
S102, calculating strong association relations between all attributes in the attribute information of the heating surface of the power plant and metal failure forms according to an FP-Growth algorithm and establishing association rules;
the specific process is as follows:
firstly, sorting the power plant heating surface attribute information with discrete data, taking each power plant device in a report as an identifier, taking the power plant heating surface attribute information of each power plant device as an affair, taking each attribute in the power plant heating surface attribute information as an item, and taking the set of all the affairs as an affair set;
secondly, scanning the transaction set for the first time, calculating the support degree count of each item in each transaction, presetting a minimum support degree threshold, and deleting if the support degree count is smaller than the minimum support degree; if the support degree is larger than or equal to the minimum support degree, reserving; and then sorting the frequent items according to the support count in a descending order.
Then, scanning the transaction set for the second time, creating a mark as an equipment node when reading in one transaction, then forming a path from the root node to the equipment node until each transaction is mapped to one path of the FP-tree, and forming the FP-tree after reading in all the transactions;
then, sequentially extracting corresponding item sets upwards from the end node of each path of the FP-tree, and if the support degree of the item sets is greater than or equal to the minimum support degree, keeping the item sets as a frequent item set 1; if the support degree of the item set is less than the minimum support degree, deleting the item set;
and finally, outputting the strong association rule.
Preferably, the metal failure modes herein include: long term overheating, short term overheating, wear, vapor side oxygen corrosion, stress corrosion cracking, thermal fatigue, high temperature corrosion, dissimilar metal welding, and quality control errors.
S103, sorting the association rules in a descending order according to the confidence coefficient, and dividing a plurality of previous association rules into an early warning set;
the higher the confidence coefficient is, the higher the probability of the metal failure is, the higher the association rule item is selected according to the ranking of the confidence coefficient.
And S104, matching the data of the heating surface of the power plant to be detected with the association rule, and sending out an early warning signal if the matched association rule item is in an early warning set.
The method is based on a data analysis method, assists the supervision work of metal failure, and provides early warning for possible failure of the heating surface. Aiming at data in a power plant heating surface inspection report of an electric academy, a strong association relation between power plant heating surface attribute information and a metal failure form is established based on an FP-Growth algorithm, a reliable association rule is extracted, a failure warning effect is provided for metal equipment with similar characteristics in an in-service unit, the purpose of predicting equipment failure is achieved, related personnel are reminded to pay attention to and inspect the equipment, and the metal equipment failure is prevented.
For ease of understanding, in an alternative embodiment, a specific process of the method for analyzing the failure of the heating surface of the power plant is provided as follows:
630 parts of metal failure inspection reports and metal conventional inspection reports of a certain power saving department in 2018 all year round relate to 141 units of 45 power plants, wherein the metal failure inspection reports comprise 450 parts and the conventional inspection reports comprise 180 parts. And extracting characteristic data of the metal inspection in the 630 reports, and establishing a metal inspection database.
Firstly, extracting attribute information of a heating surface of a power plant from a report;
part of the unit data is selected, as shown in tables 1 and 2:
TABLE 1
TABLE 2
Step 2, carrying out data discretization processing on the data;
the treatment results are shown in tables 3 and 4 below:
TABLE 3
TABLE 4
Step 3, establishing association analysis according to the FP-Growth algorithm, extracting strong association rules, and sorting in a descending order according to confidence;
the calculation results are shown in tables 5 and 6 below:
TABLE 5
Where table 5 is an association rule and confidence ranking for long term overheating (SX ═ 1), in table 5, the one rule with the highest confidence is interpreted as: when the operation time (YX ═ 9) is 4.5 to 5 ten thousand hours and the aging class (LH ═ 6) is 6, long-term overheating of the metal may occur, and the probability of occurrence is 72.61. According to the rules, the occurrence frequency of the accumulated running time (YX) and the accumulated overtemperature time (CW) is high, and the confidence coefficient of the long-term overheating is high, so that the two factors mainly influence the long-term overheating. Second, the aging Level (LH), inner and outer three rings (NW), and coal type (MZ) also have relatively significant effects on long term overheating.
TABLE 6
Table 6 shows the association rule and confidence ranking of the short term overheating (SX ═ 2), in table 6, the factors with higher confidence appear more than the long term overheating, the reasons for the short term overheating are more, the complexity is higher, and it has a certain relationship not only with the over-temperature time (CW), the aging Level (LH), and the scale thickness (YHP), but also with the material of the metal (CZ) and the manufacturer (CJ).
Step 4, matching the metal information of the power plant unit equipment to be detected with the association rule to generate failure early warning;
the early warning results are shown in table 7 below:
TABLE 7
The probability that the 7 power plant unit devices generate metal failure is high, failure early warning is generated to prompt relevant workers to pay attention and check the devices, and the metal device failure condition is prevented.
Referring to fig. 2, in an alternative embodiment, there is provided a power plant heating surface failure analysis apparatus, including: the method comprises the following steps: the system comprises a data extraction module, a data association calculation module, a data sorting module and a data matching early warning module;
the data extraction module is used for extracting power plant heating surface attribute information from a power plant heating surface inspection report and carrying out discretization processing on the power plant heating surface attribute information;
the data association calculation module is used for calculating strong association relations between all attributes in the attribute information of the heating surface of the power plant and the metal failure modes according to the FP-Growth algorithm and establishing association rules;
the data sorting module is used for sorting the association rules in a descending order according to the confidence coefficient and dividing a plurality of previous association rules into an early warning set;
the data matching early warning module is used for matching the data of the heating surface of the power plant to be detected with the association rules, and if the matched association rule items are in the early warning set, an early warning signal is sent out.
The device provided by the embodiment can assist the supervision work of metal failure from the perspective of data analysis, and provide early warning for possible failure of the heating surface. Aiming at data in a power plant heating surface inspection report of an electric academy, a strong association relation between power plant heating surface attribute information and a metal failure form is established based on an FP-Growth algorithm, and a reliable association rule is extracted.
Referring to fig. 3, an embodiment of the present invention further provides a failure analysis device for a heating surface of a power plant, where the failure analysis device for a heating surface of a power plant may be any type of intelligent terminal, such as a mobile phone, a tablet computer, a personal computer, and so on.
Specifically, this power plant heating surface failure analysis equipment includes: one or more control processors and memory, one control processor being exemplified in fig. 3.
The control processor and the memory may be connected by a bus or other means, as exemplified by the bus connection in fig. 3.
The memory is a non-transitory computer-readable storage medium, and may be used to store a non-transitory software program, a non-transitory computer-executable program, and modules, such as program instructions/modules corresponding to the failure analysis device of the heating surface of the power plant in the embodiment of the present invention, for example, the data extraction module, the data association calculation module, the data sorting module, and the data matching early warning module shown in fig. 2; the control processor executes various functional applications and data processing of the power plant heating surface failure analysis device by running the non-transitory software program, the instructions and the modules stored in the memory, so that the power plant heating surface failure analysis method of the embodiment of the method is realized.
The memory may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created from use of the power plant heating surface failure analysis device, and the like. Further, the memory may include high speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, the memory optionally includes memory remotely located from the control processor, and the remote memory may be connected to the power plant heating surface failure analysis facility via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The one or more modules are stored in the memory and, when executed by the one or more control processors, perform the method for analyzing the failure of the heating surface of the power plant in the above-described method embodiment, for example, perform the above-described method steps S101 to S104 in fig. 1, and implement the functions of the apparatus in fig. 2.
Embodiments of the present invention also provide a computer-readable storage medium storing computer-executable instructions, which are executed by one or more control processors, for example, by one of the control processors in fig. 3, and may cause the one or more control processors to execute the method for analyzing a failure of a heating surface of a power plant in the above-described method embodiment, for example, execute the above-described method steps S101 to S104 in fig. 1, and implement the functions of the apparatus in fig. 2.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, may be located in one place, or may be distributed over a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
Through the above description of the embodiments, those skilled in the art can clearly understand that the embodiments can be implemented by software plus a general hardware platform. Those skilled in the art will appreciate that all or part of the processes of the methods of the above embodiments may be implemented by hardware related to instructions of a computer program, which may be stored in a computer readable storage medium, and when executed, may include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read Only Memory (ROM), a Random Access Memory (RAM), or the like.
While the preferred embodiments of the present invention have been described in detail, it will be understood by those skilled in the art that the foregoing and various other changes, omissions and deviations in the form and detail thereof may be made without departing from the scope of this invention.