Software generation method and software generation system
The software generation method uses a computer, wherein the computer includes a control unit and a storage unit; the storage unit stores manufacturing log data that includes sensor data acquired in one or both of a manufacturing process and an inspection process, and environmental configuration information that relates to a manufacturing device or an inspection device from which the sensor data are acquired for each component or product; and the control unit reads the manufacturing log data from the storage unit, reads the environment configuration information from the storage unit, constructs a causal inference model based on the manufacturing log data, constructs an expanded causal inference model by expanding the causal inference model using the environment configuration information, generates a contracted model by contracting the expanded causal inference model to a causal relation of prescribed target data of interest, and generates prescribed application software by reading the contracted model.
1. A software generation method for generating software by using a computer,
wherein the computer includes a control unit and a storage unit,
the storage unit stores manufacturing log data and environment configuration information that includes sensor data acquired in one or both of a manufacturing process and an inspection process, bill of materials (BOM) information that specifies a product configuration, device type information and construction starting history information, and
the control unit performs:
a result value receiving step of reading the manufacturing log data from the storage unit,
an environment configuration information reading step of reading the environment configuration information from the storage unit,
an expanded causal inference model construction step of constructing a causal inference model based on the manufacturing log data and constructing an expanded causal inference model by expanding the causal inference model by using the environment configuration information,
a model contraction step of generating a contracted model by contracting the expanded causal inference model to a causal relation of prescribed target data of interest, and
a software generation step of reading the contracted model and generating prescribed application software,
wherein the causal inference model is constructed for each component included in the BOM information and is integrated to the expanded causal inference model in the expanded causal inference model contraction step,
wherein the expanded causal inference model includes a probability distribution of the manufacturing loci data in a product form for each manufacturing device and each type of the manufacturing device in the expanded causal inference model construction step, and
wherein the storage unit stores the prescribed target data of interest for each application software, and the expanded causal inference model is contracted by being restricted and integrated to a causal relation of the target data of interest in the model contraction step.
2. The software generation method according to claim 1 ,
wherein a Bayesian network is used in the expanded causal inference model construction step.
3. The software generation method according to claim 1 ,
wherein the expanded causal inference model includes a probability distribution of the manufacturing log data in a product form for each manufacturing device in the expanded causal inference model construction step.
4. The software generation method according to claim 1 ,
wherein the storage unit stores, as the target data of interest, a failure mode occurrence ratio and information specifying a process as a condition thereof in association with machine difference analysis application software, and the expanded causal inference model is contracted by being restricted and integrated to the failure mode occurrence ratio with the information that specifies the process as the condition in model contraction step.
5. A software generation system comprising:
a processor;
a control unit; and
a storage unit,
wherein the storage unit stores manufacturing log data and environment configuration information that includes sensor data acquired in one or both of a manufacturing process and an inspection process, bill of materials (BOM) information that specifies a product configuration, device type information and construction starting history information, and
the control unit performs
a result value receiving step of reading the manufacturing log data from the storage unit,
an environment configuration information reading step of reading the environment configuration information from the storage unit,
an expanded causal inference model construction step of constructing a causal inference model based on the manufacturing log data and constructing an expanded causal inference model by expanding the causal inference model by using the environment configuration information,
a model contraction step of generating a contracted model by contracting the expanded causal inference model to a causal relation of prescribed target data of interest, and
a software generation step of reading the contracted model and generating prescribed application software,
wherein the causal inference model is constructed for each component included in the BOM information and is integrated to the expanded causal inference model in the expanded causal inference model contraction step,
wherein the expanded causal inference model includes a probability distribution of the manufacturing loci data in a product form for each manufacturing device and each type of the manufacturing device in the expanded causal inference model construction step, and
wherein the storage unit stores the prescribed target data of interest for each application software, and the expanded causal inference model is contracted by being restricted and integrated to a causal relation of the target data of interest in the model contraction step.