Method for Product Design Time Forecasting Based on Support Vector Regression with Probabilistic Constraints

Figures & data

TABLE 1 Training and Testing Data of Injection Model Design

Molds		Input Data
No.	Name	SC	MD	WGV	CN	MS	FFN	Desired Outputs(h)	MCTs(h)
1	Global handle	L	L	L	4	3.1	3	23	26
2	Water bottle lid	H	L	H	4	0.56	7	45.5	49
3	Medicine lid	H	M	VL	4	1.5	6	37	41
4	Footbath basin	VL	VL	VL	1	0.5	3	10	14
5	Litter basket	L	M	H	1	2.1	12	42.5	48
6	Plastic silk flower	L	M	M	1	7.1	4	29.5	34
7	Dining chair	M	H	L	1	0.5	15	48	53
8	Spindling bushing	H	VL	L	2	8.07	2	30	35
9	Three-way pipe	H	L	L	1	0.45	5	24.5	27
10	Hydrant shell	VH	H	M	1	3	7	49	54
…	…	…	…	…	…	…	…	…	…
71	Paper-lead pulley	L	M	H	8	6.1	6	55	57
72	Winding tray	M	M	VH	1	2.18	7	41.5	44

TABLE 2 Comparison of Forecast Results from Five Different Models

		Forecast Results(h)
No.	Designed Outputs(h)	F -SVM	par--SVR	KA	K-KA	PC-SVR
T1	31	35.315	44.577	48.335	34.730	34.901
T2	41	40.672	49.238	52.146	39.868	40.635
T3	62	62.029	64.201	64.780	61.983	61.348
T4	34.5	33.313	32.596	32.945	32.444	32.850
T5	16	16.424	18.193	22.288	16.548	16.475
T6	32.5	32.965	33.813	37.085	31.737	33.323
T7	42.5	40.243	47.539	49.658	42.376	40.572
T8	16.5	15.394	13.987	20.691	16.297	15.188
T9	22	21.521	16.711	18.599	18.724	20.870
T10	54.5	46.391	48.204	49.077	46.598	47.771
T11	55	54.149	52.901	52.474	51.990	55.243
T12	41.5	41.752	48.769	50.313	43.983	43.387

TABLE 3 Error Statistics of Five Forecast Models

	Testing Results
Model	RMSE	MAPE	MAE
F -SVM	2.793	0.045	1.650
par--SVR	5.943	0.146	4.827
KA	7.579	0.199	6.267
K-KA	3.011	0.057	2.104
PC-SVR	2.500	0.050	1.758

FIGURE 1 Testing results of PC-SVR.

TABLE 4 Optimal Model Parameters of Regression Models

	par--SVR			KA		K-KA			PC-SVR
Dataset	C			C		C	D		C	D
BH	8686.324	0.263	0.437	762.038	1.575	295.366	216.858	1.221	9081.464	58.368	0.782
CST	9979.311	0.998	0.891	995.192	1.398	974.938	1.397	1.775	9088.081	72.819	0.803

TABLE 5 Comparison of Regression Performance

	par--SVR			KA			K-KA			PC-SVR
Dataset	RMSE	MAPE	MAE	RMSE	MAPE	MAE	RMSE	MAPE	MAE	RMSE	MAPE	MAE
BH	0.227	0.532	0.158	0.211	0.858	0.149	0.212	0.833	0.154	0.180	0.446	0.127
CST	0.032	0.052	0.028	0.034	0.042	0.020	0.034	0.041	0.020	0.034	0.062	0.039