A method and system for diagnosing faults of irradiation device

Abstract

The present invention relates to the technical field of irradiation devices, and discloses a method and system for diagnosing faults of irradiation devices. The diagnostic method comprises the following steps: collecting characteristic information of the irradiation device to be diagnosed, performing a first fault identification in combination with a fault database, and obtaining a first diagnostic result; performing a second fault identification in combination with grey correlation calculation on characteristic information of the fault that cannot be identified in the first fault identification, and obtaining a second diagnostic result of the irradiation device to be diagnosed; and taking disposal measures to eliminate the fault of the irradiation device to be diagnosed according to the first diagnostic result and the second diagnostic result, thereby solving the problem that the existing irradiation device fault diagnosis is single-professional and on-site personnel cannot quickly eliminate the fault.

Description

Technical Field

[0001] The present invention relates to the technical field of irradiation devices, and in particular to a fault diagnosis method and system for irradiation devices. Background Art

[0002] Irradiation devices are used in the fields of medicine, video, polymer and environmental protection. Irradiation devices affect the irradiated objects through radiation. During the irradiation process, radiation will affect people and the environment, so irradiation devices must be safe and reliable. At present, irradiation devices mainly monitor and identify equipment failures by collecting equipment information. However, the built-in fault prompt method is too simple, the information expression is too professional, and the personnel skills are required to be high. These characteristics make it difficult for on-site operation staff to understand the essential characteristics of the fault and obtain valuable information from it. For personnel who do not have the skills to maintain the device, they cannot take further measures to eliminate the fault and quickly restore the device to normal operation. Summary of the invention

[0003] The present invention provides a method and system for diagnosing faults of an irradiation device, so as to solve the problem that the existing irradiation device fault diagnosis is a single profession and the on-site personnel are unable to quickly eliminate the faults.

[0004] In order to achieve the above object, the present invention is implemented by the following technical solutions: In a first aspect, the present invention provides a method for diagnosing faults of an irradiation device, comprising the following steps: Step 1: Collect characteristic information of the irradiation device to be diagnosed, perform the first fault identification based on the characteristic information and the established fault database, obtain the first diagnosis result and perform fault elimination; The fault database stores characteristic information of several types of faulty irradiation devices and corresponding processing operations; Step 2: For the characteristic information of the fault that cannot be identified in the first fault identification, the resolution coefficient is calculated in combination with the fault database, and the correlation degree with various characteristic information in the fault database is obtained in combination with the resolution coefficient. Based on the correlation degree and a pre-set correlation threshold, a second diagnosis result of the irradiation device to be diagnosed is obtained; Step 3: Take measures to eliminate the fault of the irradiation device to be diagnosed according to the first diagnosis result and the second diagnosis result.

[0005] Furthermore, the characteristic information is collected through sensors, and the characteristic information includes: cylinder valve opening, dosage rate, water well water level, ventilation coefficient, air temperature, air humidity, photoelectric switch, conveyor chain load, door bolt position and one or more of motor current.

[0006] Further, the first fault identification includes: comparing the collected characteristic information of the irradiation equipment to be diagnosed with the characteristic information of the irradiation equipment having a fault stored in the fault database to determine the fault type; If the characteristic information is the same as the characteristic information stored in the database, the corresponding processing operation is output as the first diagnosis result.

[0007] Furthermore, the calculating of the resolution coefficient in combination with the fault database includes: calculating the resolution coefficient corresponding to each fault based on characteristic information of several types of irradiation devices having faults in the fault database in combination with an ant colony algorithm; The steps include: Step 201: Initialize the ant colony algorithm; Initializing the ant colony algorithm includes: setting the initial value of the resolution coefficient, the number of ants, the number of iterations, pheromones and constraints; The pheromone includes a pheromone table, a pheromone importance parameter, a heuristic factor importance parameter, a pheromone enhancement coefficient, and a pheromone volatility coefficient, and the constraint conditions include: the correlation corresponding to the determined resolution coefficient is greater than a first threshold, and is less than a second threshold after a predetermined number of iterations, and the first threshold is greater than the second threshold; Step 202: extracting a first characterization sequence from characteristic information of a faulty irradiation device in a fault database, calculating a correlation between the first characterization sequence and a pre-stored characterization sequence, and increasing the value resolution coefficient in sequence according to a predetermined fixed value, and performing an iterative search in combination with an ant colony algorithm; Step 203: Determine the optimal path information after iterative search, and update the pheromone table accordingly; Step 204: obtaining a resolution coefficient that satisfies the constraint condition within the number of iterations; Step 205: Repeat steps 201 to 204 until the resolution coefficient corresponding to each fault in the fault data is obtained.

[0008] Furthermore, the acquisition of the correlation with various characteristic information of the fault database includes: Performing grey correlation calculation on the characteristic information of the fault that cannot be identified in the first fault identification in combination with the pre-stored representation sequence in a sequence database and the resolution coefficient to obtain a plurality of correlation degrees; The sequence database stores pre-stored characterization sequences of characteristic information of several types of faulty irradiation devices.

[0009] Furthermore, the acquisition of the correlation with various characteristic information of the fault database further includes the following steps: Extracting several second characterization sequences from the characteristic information of the fault that cannot be identified in the first fault identification, and performing grey correlation calculation on the second characterization sequences and all pre-stored characterization sequences in the sequence database and the corresponding resolution coefficients to obtain several correlation degrees; The first characterization sequence, the second characterization sequence and the pre-stored characterization sequence are all formed by normalizing the corresponding feature information; The normalization process includes: converting the characteristic information into a uniform predetermined numerical range.

[0010] Among them, the first characterization sequence is composed of normalized characteristic information of the irradiation device that has failed in the fault database, the second characterization sequence is composed of normalized characteristic information of the irradiation device to be diagnosed, and the pre-stored characterization sequence is composed of normalized characteristic information of the irradiation device that has failed.

[0011] Furthermore, the pre-stored characterization sequences stored in the sequence database are all subjected to data fuzzy processing, and the data fuzzy processing includes: adjusting the normalized pre-stored characterization sequences according to a preset predetermined value; The predetermined values ​​include, from small to large, a lower limit value, a lower alarm value, a normal value, an upper alarm value, and an upper limit value; The adjustment includes taking the nearest predetermined value downward.

[0012] Furthermore, the obtaining of the second diagnosis result of the irradiation device to be diagnosed based on a plurality of correlation degrees combined with a preset correlation threshold value includes: Sort the obtained several correlations from large to small; It is determined whether the maximum value of the correlation degree exceeds the correlation threshold. If it does not exceed, the manual diagnosis is fed back as the second diagnosis result. If it exceeds, the fault type corresponding to the correlation degree is fed back as the second diagnosis result.

[0013] Further, if exceeded, feeding back the fault type corresponding to the correlation as the second diagnosis result includes: when the number of correlations exceeding the correlation threshold is 1, feeding back a single second diagnosis result of the fault type corresponding to the correlation; When the number of correlation degrees exceeding the correlation threshold is greater than 1, multiple second diagnosis results of the fault types corresponding to the correlation degrees exceeding the correlation threshold are fed back.

[0014] In a second aspect, the present invention provides a system for diagnosing fault types of irradiation devices, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of any of the above-mentioned methods when executing the computer program.

[0015] Beneficial effects: 1. The present invention provides a method and system for diagnosing the fault type of an irradiation device, which greatly improves the accuracy, comprehensiveness and convenience of troubleshooting by conducting a two-step method to troubleshoot and eliminate the faults respectively.

[0016] 2. In the present invention, the accuracy of irradiation device fault diagnosis is improved by combining the fault database and grey correlation calculation in the second step.

[0017] 3. In the present invention, the ant colony algorithm is further combined to optimize the calculation of the resolution coefficient in the grey correlation, thereby improving the credibility of the correlation calculation and further improving the accuracy of fault diagnosis.

[0018] 4. The diagnostic results of the irradiation device obtained by integrating the fault database with the correlation calculation avoid misdiagnosis and missed diagnosis and the situation where on-site staff are unable to take further disposal measures. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 This is a flow chart of a method for diagnosing fault types of an irradiation device according to Embodiment 1 of the present invention; Figure 2 This is a flow chart of the ant colony algorithm of embodiment 2 of the present invention. DETAILED DESCRIPTION

[0020] The technical solution of the present invention is described clearly and completely below. Obviously, the described embodiments are only a part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0021] Unless otherwise defined, the technical terms or scientific terms used in the present invention shall have the usual meanings understood by persons with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. Similarly, words such as "one" or "one" do not indicate quantity restrictions, but indicate the existence of at least one. Words such as "connect" or "connected" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the object being described changes, the relative positional relationship also changes accordingly.

[0022] See also Figure 1 , the embodiment of the present application provides a method for diagnosing faults of an irradiation device, comprising: Step 1: Collect characteristic information of the irradiation device to be diagnosed, perform the first fault identification based on the characteristic information and the established fault database, and obtain the first diagnosis result; Specifically, the first fault identification includes: comparing the collected characteristic information of the irradiation equipment to be diagnosed with the characteristic information of the faulty irradiation device stored in the fault database to determine the fault type; if the characteristic information is the same as the characteristic information stored in the database, the corresponding processing operation is output as the first diagnostic result.

[0023] The fault database stores characteristic information of several types of faulty irradiation devices and corresponding processing operations, wherein the fault types and corresponding processing operations can be built based on corresponding maintenance manuals or expert knowledge.

[0024] Among them, the characteristic information is collected by sensors, and the characteristic information includes: cylinder valve opening, dosage rate, water well water level, ventilation coefficient, air temperature, air humidity, photoelectric switch, transmission chain load, door bolt position and motor current; It should be noted that if the first diagnosis result is directly obtained, there is no need to perform subsequent steps, and the irradiation device to be diagnosed can be directly treated and the fault eliminated according to the first diagnosis result.

[0025] Step 2: For the characteristic information of the fault that cannot be identified in the first fault identification, the resolution coefficient is calculated in combination with the fault database, and the correlation degree with various characteristic information in the fault database is obtained in combination with the resolution coefficient. Based on the correlation degree and a pre-set correlation threshold, a second diagnosis result of the irradiation device to be diagnosed is obtained; Among them, the normalization process is to convert the characteristic information into a unified predetermined value range, and the data fuzzy process is to take the nearest value of the pre-stored characterization sequence after the normalization process according to the preset predetermined value, and the preset values ​​include from small to large: lower limit value, lower alarm value, normal value, upper alarm value and upper limit value; In this embodiment, the lower limit value is set to 0, the lower alarm value is set to 0.25, the normal value is set to 0.5, the upper alarm value is set to 0.75, and the upper limit value is set to 1.

[0026] Step 2 specifically includes the following steps: Step 201: Initialize the ant colony algorithm; Initializing the ant colony algorithm includes: setting the initial value of the resolution coefficient, the number of ants, the number of iterations, pheromones, and constraints; Pheromones include pheromone table, pheromone importance parameter, heuristic factor importance parameter, pheromone enhancement coefficient and pheromone volatility coefficient; The constraint conditions include: the correlation degree corresponding to the determined resolution coefficient is greater than a first threshold value, and is less than a second threshold value after a predetermined number of iterations, and the first threshold value is greater than the second threshold value; Step 202: extracting a first characterization sequence from characteristic information of a faulty irradiation device in a fault database, calculating a correlation between the first characterization sequence and a pre-stored characterization sequence, and increasing the value resolution coefficient in sequence according to a predetermined fixed value, and performing an iterative search in combination with an ant colony algorithm; Wherein, the first characterization sequence is formed by normalizing the characteristic information of the irradiation device to be diagnosed; The calculation of correlation can be expressed as the following formula: ; ; ; ; ; in, represents a sequence of pre-stored representations, Represents the pre-stored characterization sequence parameters, Indicates the number of parameters; represents the first token sequence, represents the first characterization sequence parameter, , Indicates the number of parameters. represents the parameter difference, Indicates the first parameters, Indicates the first characterization sequence parameters; It represents the minimum value of the absolute value of the difference between two sequences. It represents the maximum value of the absolute values ​​of the two sequences; make: ; ; in, Indicates the degree of association, represents the resolution coefficient; Represents a sequence of pre-stored representations With the sequence of characters to be tested The correlation degree, The bigger the and The closer; Resolution coefficient It is determined in the range of [0,1], and the optimized resolution coefficient is calculated by using the ant colony algorithm to provide the credibility of the result; Step 203: Determine the optimal path information after iterative search, and update the pheromone table accordingly; Step 204: obtaining a resolution coefficient that satisfies the constraint condition within the number of iterations; Step 205: repeating steps 201 to 204 until the resolution coefficient corresponding to each fault in the fault data is obtained; Step 206: extracting a plurality of second characterization sequences from the characteristic information of the fault that cannot be identified in the first fault identification, and performing grey correlation calculation on the second characterization sequences and all pre-stored characterization sequences and corresponding resolution coefficients in the sequence database to obtain a plurality of correlation degrees; The sequence database stores pre-stored characterization sequences of characteristic information of several types of faulty irradiation devices, and the pre-stored characterization sequences are formed by normalizing the characteristic information of the faulty irradiation devices and then performing data fuzzy processing.

[0027] Step 206: sorting the obtained multiple association degrees from large to small; Step 207: determine whether the maximum value of the correlation degree exceeds the correlation threshold, if not, feedback the manual diagnosis as the second diagnosis result, if exceeded, feedback the fault type corresponding to the correlation degree as the second diagnosis result; When the number of correlations exceeding the correlation threshold is 1, a single second diagnosis result of the fault type corresponding to the correlation is fed back; When the number of correlation degrees exceeding the correlation threshold is greater than 1, multiple second diagnosis results of the fault types corresponding to the correlation degrees exceeding the correlation threshold are fed back.

[0028] Step 3: Take measures to eliminate the fault of the irradiation device to be diagnosed according to the first diagnosis result and the second diagnosis result.

[0029] Specifically, when the first diagnostic result is obtained, the irradiation device to be diagnosed is directly troubleshooted according to the processing operation of the first diagnostic result. When the first diagnostic result cannot be obtained, that is, the fault of the irradiation device to be diagnosed cannot be identified based on the fault database, steps 2 and 3 are executed to obtain the second diagnostic result. When the second diagnostic result is a manual diagnosis, the irradiation device is troubleshooted according to the manual diagnostic result. When the second diagnostic result is a single or multiple diagnostic results, the corresponding processing operation is searched in the fault database according to the fault type corresponding to the second diagnostic result to perform troubleshooting.

[0030] Example 2 In this embodiment, characteristic information of the cylinder valve opening, dose rate, water well water level, ventilation coefficient, air temperature, air humidity, photoelectric switch, conveyor chain load, bolt position and motor current of a to-be-diagnosed irradiation device is collected, and a fault database and a sequence database are established according to typical daily faults of the irradiation device. 20 common faults are set in the database for the first fault identification. If the fault type of the to-be-diagnosed irradiation device cannot be identified in the fault database, the above 10 characteristic information are normalized to form the following to-be-diagnosed characterization sequence : ; Then perform the second fault identification, see Figure 2 In the ant colony algorithm of this embodiment, the initial value of the resolution coefficient is set to 0, the number of iterations is set to 200 times, that is, the resolution coefficient is increased by 0.005 in each iteration until the maximum resolution coefficient is 1, the number of ants is set to 50, and the pheromone related parameters are set to: initialize the pheromone table (all elements inside the matrix are 1), the pheromone importance parameter is 1, the heuristic factor importance parameter is 5, the hormone enhancement coefficient is 2, and the pheromone volatility coefficient is 0.3; In the constraint condition, the first threshold is set to 0.9 and the second preset value is set to 0.7; In the fault database, the fault of "abnormal dose in irradiation room" is mainly manifested as the ambient radiation dose level in the hall inside the irradiation room exceeding the standard. Other parameters will not change. The corresponding pre-stored characterization sequence in the sequence database It is expressed as: ; The association degree is calculated for 20 pre-stored representation sequences in the sequence database to obtain the association degree matrix: ; Sort all the associations in the association matrix from large to small and find that the maximum value is , and is greater than the set correlation threshold of 0.9, and the number is 1, a single second diagnostic result is output, and the corresponding fault type is "irradiation chamber dose abnormality". The corresponding processing operation is searched in the fault database for troubleshooting.

[0031] An embodiment of the present application also provides a system for diagnosing fault types of irradiation devices, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of any method in the above embodiments are implemented.

[0032] The preferred specific embodiments of the present invention are described in detail above. It should be understood that a person skilled in the art can make many modifications and changes based on the concept of the present invention without creative work. Therefore, any technical solution that can be obtained by a person skilled in the art through logical analysis, reasoning or limited experiments based on the concept of the present invention on the basis of the prior art should be within the scope of protection determined by the claims.

Claims

1. A method for diagnosing faults of an irradiation device, characterized in that: The steps include: Step 1: Collect characteristic information of the irradiation device to be diagnosed, perform the first fault identification based on the characteristic information and the established fault database, obtain the first diagnosis result and perform fault elimination; The fault database stores characteristic information of several types of faulty irradiation devices and corresponding processing operations; Step 2: For the characteristic information of the fault that cannot be identified in the first fault identification, the resolution coefficient is calculated in combination with the fault database, and the correlation degree with various characteristic information in the fault database is obtained in combination with the resolution coefficient. Based on the correlation degree and a pre-set correlation threshold, a second diagnosis result of the irradiation device to be diagnosed is obtained; Step 3: Take measures to eliminate the fault of the irradiation device to be diagnosed according to the first diagnosis result and the second diagnosis result.

2. The method for diagnosing faults of an irradiation device according to claim 1, characterized in that: The characteristic information is collected through sensors, and the characteristic information includes: one or more of: cylinder valve opening, dosage rate, water well water level, ventilation coefficient, air temperature, air humidity, photoelectric switch, transmission chain load, door bolt position and motor current.

3. The irradiation device fault diagnosis method according to claim 2, characterized in that: The first fault identification includes: comparing the collected characteristic information of the irradiation equipment to be diagnosed with the characteristic information of the irradiation equipment having a fault stored in the fault database to determine the fault type; If the characteristic information is the same as the characteristic information stored in the database, the corresponding processing operation is output as the first diagnosis result.

4. The method for diagnosing fault types of irradiation equipment according to claim 1, characterized in that: The calculating of the resolution coefficient in combination with the fault database comprises: calculating the resolution coefficient corresponding to each fault based on characteristic information of several types of irradiation devices having faults in the fault database in combination with an ant colony algorithm; The steps include: Step 201: Initialize the ant colony algorithm; Initializing the ant colony algorithm includes: setting the initial value of the resolution coefficient, the number of ants, the number of iterations, pheromones and constraints; The pheromone includes a pheromone table, a pheromone importance parameter, a heuristic factor importance parameter, a pheromone enhancement coefficient, and a pheromone volatility coefficient, and the constraint conditions include: the correlation corresponding to the determined resolution coefficient is greater than a first threshold, and is less than a second threshold after a predetermined number of iterations, and the first threshold is greater than the second threshold; Step 202: extracting a first characterization sequence from characteristic information of a faulty irradiation device in a fault database, calculating a correlation between the first characterization sequence and a pre-stored characterization sequence, and increasing the value resolution coefficient in sequence according to a predetermined fixed value, and performing an iterative search in combination with an ant colony algorithm; Step 203: Determine the optimal path information after iterative search, and update the pheromone table accordingly; Step 204: obtaining a resolution coefficient that satisfies the constraint condition within the number of iterations; Step 205: Repeat steps 201 to 204 until the resolution coefficient corresponding to each fault in the fault data is obtained.

5. The method for diagnosing fault types of irradiation equipment according to any one of claims 1 to 4, characterized in that: The acquisition of the correlation degree with various characteristic information of the fault database includes: Performing grey correlation calculation on the characteristic information of the fault that cannot be identified in the first fault identification in combination with the pre-stored representation sequence in a sequence database and the resolution coefficient to obtain a plurality of correlation degrees; The sequence database stores pre-stored characterization sequences of characteristic information of several types of faulty irradiation devices.

6. The method for diagnosing fault types of irradiation equipment according to claim 5, characterized in that: The acquisition of the correlation degree with various characteristic information of the fault database also includes the following steps: Extracting several second characterization sequences from the characteristic information of the fault that cannot be identified in the first fault identification, and performing grey correlation calculation on the second characterization sequences and all pre-stored characterization sequences in the sequence database and the corresponding resolution coefficients to obtain several correlation degrees; The first characterization sequence, the second characterization sequence and the pre-stored characterization sequence are all formed by normalizing the corresponding feature information; The normalization process includes: converting the characteristic information into a uniform predetermined numerical range.

7. The method for diagnosing fault types of irradiation equipment according to claim 6, characterized in that: The pre-stored characterization sequences stored in the sequence database are all subjected to data fuzzy processing, and the data fuzzy processing includes: adjusting the normalized pre-stored characterization sequences according to a preset predetermined value; The predetermined values ​​include, from small to large, a lower limit value, a lower alarm value, a normal value, an upper alarm value, and an upper limit value; The adjustment includes taking the nearest predetermined value downward.

8. The method for diagnosing fault types of irradiation equipment according to claim 7, characterized in that: The method of obtaining a second diagnosis result of the irradiation device to be diagnosed based on a plurality of correlation degrees combined with a preset correlation threshold comprises: Sort the obtained several correlations from large to small; It is determined whether the maximum value of the correlation degree exceeds the correlation threshold. If it does not exceed, the manual diagnosis is fed back as the second diagnosis result. If it exceeds, the fault type corresponding to the correlation degree is fed back as the second diagnosis result.

9. The method for diagnosing fault types of irradiation equipment according to claim 8, characterized in that: The feedback of the fault type corresponding to the correlation as the second diagnosis result if exceeded includes: when the number of correlations exceeding the correlation threshold is 1, feedback of a single second diagnosis result of the fault type corresponding to the correlation; When the number of correlation degrees exceeding the correlation threshold is greater than 1, multiple second diagnosis results of the fault types corresponding to the correlation degrees exceeding the correlation threshold are fed back.

10. A fault type diagnosis system for an irradiation device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method described in any one of claims 1 to 9 are implemented.

Images